Deep Learning, xgb, BERT COPY Flashcards

Question

How does a basic one-layer RNN work? What 3 sets of weights are learned, and how are they applied to an input?

Answer 1

An RNN has a **common "structure" or "hidden layer"** that is applied sequentially to each time step in the input structure; for example, words in a sentence. At each application, there are basically 2 things that determine the activations 's' of the hidden layer: the input, and the weight matrix Wx that connects the input to the hidden layer; and **the activations of the previous application of the hidden layer**, and the weight matrix Ws that connects the previous activations to the hidden layer. The two matrix-vector products are calculated, summed, and passed through the activation function. Then, a third matrix is learned which connects the activations of the hidden layer to the output layer. (Then maybe there's an activation like sigmoid.) Depending on the architecture, this might be evaluated at every step, or at just the last step, etc. Here are 3 different ways of showing the same basic network; the first shows the key formulas.

Answer 2

RNNs use the activations of the previous layer to figure out the activations of the current layer. This is useful for using context: if the last two words were "throw the", the next word might be "ball"; if yesterday's stock price was high, odds are it'll be high today too.

Answer 3

In an RNN, both the input vector x and the previous activation vector s are multiplied by their own respective weight matrices to get new vectors of the same length, which are summed to get the final value. This is where the formula activation([Wx]\*x + [Ws]s\_t-1) comes from. But this is not actually that weird, because it can just be thought of as x and s\_t-1 being lined up into one vector and multiplied by one weight matrix!

Answer 4

If you're confused, think about it in the Elman diagram way again. It's pretty intuitive: the first layer recieves the input and the first-layer activation from the previous iteration. Similarly, the nth layer at time step trecieves the activation of the n-1st layer at time t, and the activation of the nth layer at time t-1. Sometimes each layer has the same weight matrix, except specific ones for the first input and last output. Other times it's different and there's fewer shared matrices.

Answer 5

Backpropogation through time

Answer 6

We need to update 3 weight matrices: Wy, Ws, and Wx. So we need to find the derivative of the loss function with respect to each matrix (or the derivative w.r.t ecah of the parameters within each matrix). Because some matrices are called more than once in the **chain of dependencies**, we need to go back in time and encorporate all of those calls. The key is the chain of dependencies. So if we're looking at the loss function at time step 3, the y matrix Wy (which connects the hidden layer to the output) only has one invocation in this particular dependency chain for this time step, so the computation is easy. But if we're looking at Ws or Wx, each of those was used at 3 separate times in the past, so we need to find the derivative factoring in each of those invocations using the chain rule.

Answer 7

(I'm *pretty sure* the followi) If a single input has n outputs, that's basically n instances where the loss function can be calculated and backpropogation can occur. So if there's 3 outputs, the first output will be used to update Ws based on one invocation; the second output will again be used to update 2s based on 2 invocations; and the 3rd uses 3 invocations. And similarly for Wx; Wy always only has 1 relevant invocation in the chain of dependencies. This makes sense: if we have n outputs, such as if we're labeling POS for the words in a sentence, we basically have n unique predictions, so even if it's just one input in a sense, we have n opportunities to learn and improve our predictions. Now I'm sure that, rather than updating the weights after each of these, you could instead accumulate the gradients, average them, and then make an "aggregate update", similar to how with batch gradient descent you store a few individual-point gradients, average them, and take a step.

Answer 8

Vanishing gradients lead to "bad long-term memory". Basically, when we're trying to update Wx or Ws based on the output at a very late time step, we find the derivative of the contribution of that matrix W from all previous time steps. But the derivative for early time steps is a *lot* of derivatives chained together, leading to vanishing gradients. So when we're updating based on a late outcome, the contribution of an earlier part of the input vanishes. This can be bad: words at the beginning of a sentence can have a big impact on the meaning of the end of the sentence, for example. It's intuitive that vanishing gradients are especially bad for RNNs: they're bad when a bunch of layers are applied in a row, because all of the potentially small gradients are getting multiplied together. Well, an RNN has a layer that can easily be applied 50 or 100+ times if the input x has 100+ time steps. The solution is LSTMs

Answer 9

"Gradient clipping": just penalize the network for creating gradients above a certain threshold

Answer 10

Long term memory! RNNs have a mechanism for using short term memory, but due to the vanishing gradients problem, they can't really effectively retain info from very long ago. LSTMs add a path to pass along and retain long term memory in addition to the short term memory pathway.

Answer 11

Learn (green), forget (yellow), remember (red), and use (blue)

Answer 12

Add and multiply just represent element-wise addition or multiplication between two entries with the same dimension The sigmoid or tanh nodes basically represent “1 layer of a neural network”, in which: * Any inputs are concatenated * The concatenated inputs are multiplied by a weight matrix and added to a bias * This output is passed through that activation function * Just like a normal NN, the output can be a vector. This means that several scalars worth of information can flow through the model and be retained, not just one scalar. This is also helped by the + and \* being pairwise rather than something like a dot product

Answer 13

Its goal is to learn relevant information from this time step's input, using the input and the previous STM (short term memory). This learned information is eventually used to update both the LTM and the STM. This gate also decides what to forget from the current STM. Intuitively, the input helps with this because the current part-of-speech might indicate that a previous part-of-speech is no longer short-term relevant, for example. I'm including the picture, but I'm definitely not concerned with nailing the mathematical details. I'm basically just putting it there for the 'ignore' part, which is the STM forget part.

Answer 14

Using the old LTM, old STM, and current input, it simply decides what information the long term memory should forget, based on the current input as well as old info.

Answer 15

It defines what the long term memory will be coming out of this cell, using the long-term info coming out of the forget gate and the short-term info coming out of the learn gate (Again I'm not too concerned with the actual math below)

Answer 16

It decides what the new STM will be. Its inputs are the new LTM, which are based on the forget gate and learn gate results, as well as the current input and old STM.

Answer 17

It is based on the newly updated STM that comes out of the use gate. Perhaps the actual new STM could be output, or I imagine there are often learned weights that transform it a bit to form a y. Like the STM is probably often a vector of key STM info, whereas the output might be a prediction of the next word or something.

Answer 18

The peephole connections basically allow the cell to make more heavy use of the previous LTM by inserting it into more locations. Notably, it lets the LTM weigh in during the learn gate, and influence what should be learned from the input.

Answer 19

Perhaps, for example, there is a verb late in the sentence, and the subject of that verb came way earlier in the sentence. “**The cat**, which already ate at about 4pm and quite enjoyed their wet food, **was full.**”

Answer 20

GRUs only have one memory vector flowing through, rather two for a separate LTM and STM, as with LSTMs. In this way, they look much more similar to normal NNs. But unlike normal NNs (which basically only have one simple gate that passes the concatenated input-and-previous-activation through 1 layer of an NN), GRUs have 2 gates. These gates work to decide which "memory cells" in the previous cell's activation should be overridden with new information, and which should be retained as a sort of long term memory. This allows the system to learn to maintain certain pieces of information for an arbitrary period of time. If you think GRUs are gonna be important to understand, you could rewatch the coursera video on them to better understand how they work and make updates at a low level.

Answer 21

Writing new text, either one word at a time or one letter Time series prediction: predicting stock prices or something

Answer 22

You construct the outcome variable as you would intuitively: you just shift the input over by one and have that be the outcome variable The reason this isn't "cheating" is **for this type of RNN task, we're just using a feed-forward RNN rather than a bidirectional RNN**. So at any given time step t, the only information available to the RNN to make predictions is the inputs at time steps t and earlier. So there's no cheating The RNN is evaluated sequentially. So it makes the t=1 prediction, then a gradient is found; then it does t=2, and gets another gradient; and so on

Answer 23

We use a method called **sequence batching**. Say our input is an entire book (visualized below by 12 letters). First we split it up into N sections, and then we split each section into sections of M letters. A batch is then a set of M letters from each of the N batches. Below N=2 and M=3; our first batch is [[1,2,3], [7,8,9]], and our second is [[4,5,6], [10,11,12]]. If you wanted to simplify this, I imagine you could just split the whole input into length-M segments and then make every N of them a batch, but not split into N sections like this. That's also conceptually simpler, and perhaps a good way to *start* thinking about it.

Answer 24

Yep! It works for any of the relevant weight matrices.

Answer 25

A probability distribution showing the odds it's a given letter. If you're predicting words, I'm pretty sure it's the same thing: you make a probability distribution showing the odds it's each of the words in the vocabulary, and you would calculate error vs the one-hot vector for the correct answer. My other thought was maybe you output a word embedding and compare it to the word embedding of the correct answer, and then at prediction time you like output the word that is closest in the embedding space to the embedding vector you predicted. But I just don't remember that being a thing: I think you just choose the maximum-lihelihood word from a probability distribution you've created, or you sample from the probability distribution if you want some randomness.

Answer 26

Backpropogation only happens within each little stretch. So in this diagram there would be 4 instances of backpropogation. But there is still information communicated across the blocks *within* each line. When the network predicts on the input 4, it recieves the activations of the RNN cell from the previous input of 3, and that information is passed across batches. It just doesn't backpropogate all the way back through multiple batches; otherwise the chain would get insanely, unproductively long, and training would take a long time. There is no info communication or backpropogation across lines.

Answer 27

No! Each application is gonna have its own idiosyncrasies with how data and batches are best divided up, how the model is constructed, how the training loop works, etc. To implement the best thing for a given application will take experience implementing RNNs, as well as experimentation to see what gives the best results.

Answer 28

A set of word embeddings is a mapping from each word in your vocabulary to a vector of a fixed length, say 768 (much shorter than your vocab size), where each word's embedding contains meaningful information about the word's meaning, its grammatical function, its relationship to other words, etc.

Answer 29

Retaining the biases of the training data. For example, the embedding for "homemaker" might be closer to "woman" than "man". Debiasing strategies become important for this reason.

Answer 30

1. It significantly reduces the dimensionality. Training is inefficient with one-hot because, if the input vector has one 1 and thousands of zeros, very few weights are lit up and thus are optimized per input. 2. They learn semantically meaningful information. They learn that "sandwich" and "hoagie" are similar, so the learning from one can immediately apply to another. That's better than having to relearn similar weights coming out of the node for sandwich and the node for hoagie.

Answer 31

In an unsupervised way, from a large and general text corpus like the set of all wikipedia articles.

Answer 32

1: Each word is mapped to its pre-learned embedding using a key-value lookup table, and that is fed to the NN rather than the word itself. This key-value lookup is the first layer in the NN. 2: There are certain applications where custom word embeddings are learned as part of the NN you're training, or where you'd fine-tune the word embeddings during training of the NN for your particular task. We did this for sentiment analysis, for example. For this, I think you instead need to use the approach you have an embedding matrix that can be multiplied by a one-hot vector to get the relevant embedding (rather than a key-value lookup table), so it can be differentiable? Yeah cuz like, if you're just grabbing the word embeddings from a lookup table, you can't optimize the weights that are going from one-hot to word embedding, because NNs optimize the weights, not the activations of neurons themselves.

Answer 33

The algorithm assumes **words that often have similar contexts are similar, and thus should have similar embeddings.**

Answer 34

King - Man + Woman = Queen :D

Answer 35

One is to use a word to predict its context, and one is to use a word's context to predict that word.

Answer 36

You put the word embedding layer between the input and the "main RNN cell", so from the perspective of the cell, the embedding *is* the input. If you're learning a custom embedding scheme while training the RNN, you can have backprop-through-time go through the embedding layer. (In this picture sigmoid just refers to an FC layer with a sigmoid activation)

Answer 37

The computer pays attention to the relevant parts of the inputs at each step of learning or prediction. For example, in image classification, just looking at the pixels that contain the phenomena of interest, or in language translation, looking at the relevant words before writing the next word in your translation. This method is big for seq-to-seq tasks like languagee translation.

Answer 38

The encoder RNN iterates over the input, updating its hidden state at every time step. Then the final hidden state of the encoder RNN is passed to the decoder RNN, which iteratively create the translated sentence one word at a time. The big drawback is **the decoder only has access to the *final* hidden state of the encoder RNN**, so it only has access to what that final state was "thinking about". Even if it's an LSTM, maybe the long-term memory is only thinking about a certain portion of the input when we reach the end, and not thinking about the whole thing, for example. It's just gonna be difficult for the encoder to learn to communicate *all* the necessary information about the input to the decoder.

Answer 39

The encoder passes *all* of its hidden states, from every time step, to the decoder, rather than just the last one. This is great: the decoder has access to a hidden state for each individual part of the input, so it can sort of understand all parts of the input equally well. Then, at each time step in the decoder (i.e. at each word it's trying to produce), it focuses on the most important parts of the input. It learns parameters during training that figure out which parts of an input are important to focus on based on what part of the output it's trying to produce. It does this basically by learning to, at a given time step, assign each of the encoder's hidden state a weight based on how important it is, and then it calculates a "context vector" which is just the weighted sum of all the encoder's hidden states. I'm not gonna get more in the weeds than that.

Answer 40

Say we're translating the sentence "I throw the ball." In English, the conjugation "throw" can be used for the subject "I", "we", or "they". But in Spanish, each of these has a unique conjugation. So when writing the word "throw" in Spanish, the decoder can't just look at the corresponding word "throw" in English; it also has to look at the subject of the sentence, so it knows how to conjugate in Spanish.

Answer 41

The decoder figures out where in the image is relevant to the particular part of the description it's currently writing. *Awesome.*

Answer 42

In "I got you a movie about Teddy bears," Teddy isn't a name But in "I got you a movie about Teddy Roosevelt," Teddy is a name

Answer 43

Bidirectional RNNs

Answer 44

It's pretty simple: there are basically "2 RNNs", one that iterates over the input from front to back, and another that goes from back to front. So 2 hidden states are learned for each input: one that uses that input and all the earlier context, and another that uses that input and all the later context. Then both of those hidden states are concatenated and passed through a single dense layer to get the prediction, which in this case is the probability that a word is a name.

Answer 45

Just training. This makes some intuitive sense: if you had regularization as a part of your objective function rather than through dropout, you would want to penalize the model for complex weights during training, but when examining the validation set you really just wanna see how good your predictions are regardless of how complex the model parameters are. So I suppose the analog is also true for dropout.

Answer 46

Normalizing the input, as usual! Subtract mean, divide by std dev. (There are some tricks to quickly approximate this process that probably aren't important rn.) This way, the network is recieving a standardized distribution of pixel values regardless of the input image, which helps training. Otherwise dim images vs bright images would be hard to treat similarly, for example.

Answer 47

1. Fewer parameters: the same set of parameters are applied again and again, making the network more simple and probably decreasing overfitting. 2. Because it's using the same weights in different places, learning from one place can be applied elsewhere. A bird will look the same in the top right vs bottom left; with an MLP the network would have to re-learn that in every location on the network, but the CNN can learn it once and apply elsewhere. In that way it's like an RNN: a word means the same thing at the beginning or end of a sentence. 3. Because we're using a square convolution, it uses spacial information more intuitively and much better than an MLP, which would recieve the input flattened into one long vector presented one row of pixels at a time.

Answer 48

The convolutional layer is going to have a convolution, or 'filter', which is a 3x3 array of learned weights. To perform a convolution, you apply it to a part of the grid by multiplying the pixel values by the corresponding weight, then summing the results, and then passing the sum through an activation function. You do that for all parts of the image (depending on stride and padding and such, but ignore that for now): you scan across the image continually applying the convolution to form the output of the layer, which is still square.

Answer 49

I'm pretty sure the most common is padding. It feels common.

Answer 50

Say a greyscale image is 28x28 pixels. It is represented by a 28x28 grid of scalar values between 0 and 255, denoting brightness at a given pixel. RGB images need to keep track of not just one color (and not just one "brightness level"), but three: red, green and blue. So it is represented by *three* 28x28 grids of scalar values between 0 and 255, with one pertaining to the "red brightness", one to blue, and one to green. So the greyscale image is represented as a (28,28) matrix. The RGB is a (28,28,3) matrix: **it has three**"**channels", and is referred to as having a "depth" of 3**: its width and height are 28, and its depth is 3.

Answer 51

The amount of pixels it moves at a time. If it's one, it scans one pixel at a time. If it's 2, it skips every other pixel. And so on.

Answer 52

3x3: On every side of the image, there will be one row/column that we can't apply the kernel to, so each side decreases in size by 2. The output is (N-2)x(N-2) 5x5: now each size loses 3 rows, so it's (N-4)x(N-4)

Answer 53

If the input is NxN, it'll become (N/2)x(Nx2), because for every row and column, a pixel is only being formed in the output for every other pixel in the input.

Answer 54

An RGB image has 3 channels, so its shape is something like (28,28,3). In a normal 28x28 image, we'd have a filter like a 5x5 array of weights, and we'd apply it at a point by multiplying the weights by the corresponding pixels, summing all the resulting numbers, and passing through an activation. The RGB case is similar, except now the filter is 5x5x3. The height and width can be whatever, but **the depth of the kernel will equal the depth of the image, so we can learn about each of the input channels.** This way we basically have three 5x5 kernels being applied to the image: one to the red values, one to blue, and one to green. Then all 5x5x3=75 results are added together, across all 3 channels, and then passed through an activation function. So conceptually, an edge detector could learn how to detect edges separately in each of the 3 colors, having one detector for each color. For example. Below is a *great* image.

Answer 55

Say we use a 5x5x3 filter, and we pad the image such that with a stride of 1, the outcome will be 28x28x\_. What will the depth be? Well we scan the width and height of the image, and at each point we apply our "three separate 5x5 filters" to the three channels, sum the 75 outputs across all 3 channels into one scalar, and pass through activation. So we’re getting one scalar at each point. That means the output is depth 1: 28x28x1. So how do we get 28x28x4? **We learn 4 *different, separate* 5x5x3 filters**. Each will result in its own 28x28x1 output, yielding a 28x28x4 output.

Answer 56

Each filter can learn something different about the input! Maybe one detects edges, one records how bright it is, one checks if the dominant color is red, etc. Or maybe they just all detect *different* types of edges. One filter can only really learn one thing, but using multiple allows us to learn more complex and varied information during each layer.

Answer 57

Somethig like (5x5x25)! Whether it's an input layer or not, all we need is for the depth in the kernel to match the depth of the input, so we can apply a 2d filter to each of the channels, and learn about all the channels.

Answer 58

It needs 45 different filters of a shape like 5x5x32. Each filter's depth needs to match the depth of the input so it can look at all the channels in the input, and each filter will produce one NxNx1 output, so we need as many filters as we want output channels.

Answer 59

A 2x2 max pooling layer will decrease the height and width of an input by half, so the output will be 14x14x3. It does this simply enough by, within each channel, looking at each 2x2 grid within the channel, and outputting the max of those 4 values. An average pooling layer does the exact same thing, but instead of outputting the max of the 4 numbers, it outputs their mean.

Answer 60

Often, we want to apply many filters to a given layer, meaning the outputs of our convolutional layers can be very large and require many parameters, which could lead to overfitting. For example, say we’re applying 1000 filters; that will add up fast. If we decrease the height and width by 2 every so often, we can offset this growing of the parameters: as we increase depth, we can decrease height and width.

Answer 61

Generally no. You would think they could, because you just take the filter and continually slide it over the input regardless of size, but the issue the size of the activation matrix would continue to be different throughout the network, and eventually you'd typically flatten the matrix into a 1d vector that you pass to a normal dense layer; but dense layers can only take inputs matching their exact length. So you need the same sized images. (I suppose you could get away with it if all you use is conv and pooling layers, and at the end your loss function can be applied to a variable-size output.)

Answer 62

To start the network, there would be several blocks of one or more convolutional layers followed by a max pooling layer. Each blocks' convolutional layers will typically use padding so the height and width of the image don't change, and thus they only change when the max pooling layers decrease them by half. We will continually learn more and more 'features', or 'channels', about the input as we go, so when combined with the max pooling layers decreasing width and height, we will go from a representation whose height and width is much larger than its depth, to the other way around: a very deep representation with small width and depth. After we achieve this through several conv-pooling blocks, we'll flatten the resulting matrix out into a 1d vector, and pass it through a few simple dense layers before outputting our prediction. The below image doesn't show the dense layers at the end.

Answer 63

A square whose width and height are some power of 2, or maybe another round-seeming number like 28

Answer 64

We're learning more and more features/pieces of information about the input. And of course as we get deeper in the network, those features/insights become more complex, as they are supposed to with simple MLPs as well.

Answer 65

The number of input channels, and the number of output channels The height and width of one of the kernels (their depth will equal the number of input channels) The stride and padding information

Answer 66

Just the height/width and the stride

Answer 67

You can apply a bunch of different rotations, zooms, crops, or reflections to your input images, resulting in lots more slightly different images. This just makes your CNN more robust to picking up the features of the image when those features are in different sizes, orientations, etc. If you're recognizing cats, this helps you identify big cats, small cats, cats on their sides, upside-down cats, etc.

Answer 68

1. **The size of your dataset:** the smaller it is, the less capable you are of retraining a gigantic network. 2. **The quality of the match between their task and yours**: if your image classification task is super similar to theirs, you need less retraining or structural alteration than otherwise. It's easier to move from dogs to wolves than from dogs to cancer detection.

Answer 69

There are already giant, well-trained networks that can classify wide arrays of images, like ImageNet. These can often be slightly reworked to transfer all that big-data learning to your small-data task, or the parameter initizations can serve as a great starting point before fine-tuning if you have enough data to do so.

Answer 70

**Little and similar**: you can use most of the layers and can't do much retraining, so maybe just replace a couple of the fully connected layers at the end, leaving all the layers before it fixed and not backpropogating through them **Lots and similar:** because you have lots of data, you should still fine-tune the architecture, but the parameters learned from the similar task are a good initialization. You'll of course swap out a layer or two at the end (as with any of these cases) just so your # of output classes is correct **Little and not similar:** Here, overfitting to our small dataset is still an issue, so we will hold the parameters from the original network as constant. But now because the datasets are different, task-specific features that the original network learns in later layers will not be useful. We can, however, still use the more abstract features from earlier layers, like textures and edge detection. So we remove most of the original layers, leaving only the beginning layers that extract more general image features. Then we add a few new layers and only backpropogate through the new ones. **Lots and not similar**: you might fine-tune the parameters from the original, or you might just totally retrain it and just use the original network's hyperparameters, like number and size of layers, as a starting place.

Answer 71

Autoencoders are a compression algorithm, or a learned means of dimension-reducing an input, then scaling it back up to its original size with as little lost information as possible. An autoencoder is basically a neural network made up of two sub-neural-networks: the encoder and the decoder. The encoder takes the input and maps it to a low-dimensional representation, and the decoder takes that low-dimensional representation and maps it back up to the original size of the image. That low-dimensional representation in the middle there is the compressed form, and the goal of the network is to get that as good as possible. The loss function is simply to compare the input to the reconstructed input: if the input was an image, you just find the pixel-level MSE between the two, so the network aims to make the output as similar to the input as it can.

Answer 72

Compression obviously: one computer could store the trained encoder, and the other could store the trained decode, and then they can send the low-dimensional representations from one to another. Denoising, which is so goddamn cool and shown below. By just storing the most "semantically meaningful" information about the input, you can drive away meaningless noise, which is good for denoising. Similarly, image reconstruction: if a little sliver of an image is missing, an autoencoder can fill it in

Answer 73

In autoencoders, the decoder needs to take a low-dimensional vector and **upsample it into an image**. Similarly, in a GAN generating images, then generator needs to take a small vector of noise and upsample it into an image. These networks start to look like reverse CNNs: CNNs slowly go from large height/width and few channels to small height/width and many channels. So these upsampling networks need to do the opposite, slowly increasing the height and width. This is what reverse convolutional layers do: they **basically apply a filter which is larger than the area it's being applie to, and doing so with a high stride like 2, so the output height and width are larger than the input's.**

Answer 74

A GAP layer, if included, would be included after all the blocks of conv/pooling layers, before the fully connected layers. It is basically an extreme version of a pooling layer: it maps every channel to one scalar, which is the mean of all the values in the channel. Often, the inputs to the dense layers are so large (so many channels of substantive height and width), that there are just too many parameters in the final dense layers, which can cause issues with overfitting. This is a way to combat that overfitting: it drastically decreases the size of the input to the dense layers, thus decreasing the number of parameters they need to have. Because of the nature of conv layers vs dense layers, oftentimes most of a network's parameters can be in those final few dense layers, so this can be a very effective way to decrease the # of params and combat overfitting.

Answer 75

VGG19, ResNet

Answer 76

Because it takes an average of all previous gradients, with a focus on recent gradients, it can smooth out learning if it happens to be jagged. If the gradients keep jumping back and forth in one of the dimensions, those will average out to about zero, and the descent will stop taking big steps in those dimensions and focus on the dimensions with a consistent direction. This is illustrated in the following picture. These are contour lines, and each line is at a constant level in the z direction with respect to itself. So this means the slopes are way more steep in the y direction than x, because height is changing over a much smaller horizontal distance. This may be easier to see if you envision it as maximizing over a hill rather than minimizing over a valley. So in this context, you can see (in blue) how the baseline slopes will be much larger in the y direction than x, causing most of each step to be a jagged movement in the y direction rather than a productive movement in the more subtle x direction. Momentum (in red) smoothes this out. (The red drawing over-exaggerates the size of the steps in that direction, but it’s just meant to illustrate how the jagged y-direction movement is decreased.)

Answer 77

The goal, similar to momentum, is to combat jagged and inefficient learning by smoothing out our steps in the direction of the gradient. The general idea of RMSprop is it keeps track of which dimensions keep having large steps and which keep having small ones, and uses that information to smooth out training by decreasing the relative size of the large ones and increasing the relative size of the small ones. It does this by dividing the size of the step in each direction by a weighted average of recent derivatives in that direction.

Answer 78

Again, the goal, similar to momentum, is to combat jagged and inefficient learning by smoothing out our steps in the direction of the gradient. In momentum, you keep a exponentially decaying weighted average of the gradients, and each iteration you take a step in the direction of that weighted average. In RMSprop, you instead keep an exponentially weighted average of the squares of each of the partial derivatives, and then to construct the “gradient” which is the direction you want to move, for each dimension you take the current partial derivative, and divide it by the square root of the exponentially decaying sum of the derivatives. That’s pretty complicated, but here’s the intuition: because we’re squaring the derivatives in the sum, they’re always positive; so **the bigger the past derivatives, the bigger the value by which we’re *dividing* the size of our current step.** Steep dimensions where learning is jagged will have large gradients, so we’ll be dividing by a large value and decreasing the size of the step; conversely, not-steep dimensions with slow learning will now have relatively larger steps, so we make proportionally more progress in that direction. This can be used to increase the learning rate, and overall learn faster. The key parts of this picture are the **top**, showing the image where each fault like has a consistent height and thus the y axis is much steeper, and the **bottom**, showing how the update is the derivative, divided by sqrt(weighted sum of squares of derivatives).

Answer 79

It takes momentum and RMSprop and puts them together. (These are both effective means of smoothing out training and making it more consistently move in the right direction in a non-jagged fashion, so this is a good idea!)

Answer 80

Adam combines momentum and RMSprop. So, ignoring an optimization or two that isn't that important for conceptual understanding, basically what you do is: Keep track of an exponentially weighted sum of the past gradients (for momentum), as well as an exponentially weighted sum of the *squares* of the past gradients (for RMSprop) Then you make your update the exponentially weighted sum of the gradients (as with momentum), but you divide it by the square root of the weighted sum of the squares of the gradients (as with RMSprop).

Answer 81

Learning rate, the size of the step. Obviously important and need to be tuned. Then there is Beta1, which determine the rate at which the exponentially weighted sum of the gradients drops off (i.e. how quickly old values disappear towards zero), and Beta2, which is the same thing for the weighted sum of the squares of gradients used in RMSprop. Beta1 and Beta2 are more commonly not messed with and just left to the default values.

Answer 82

A GAN, or generative adversarial network, is a model essentially composed of two separate neural networks: a generator and a discriminator. The generator recieves as input a vector of random noise and transforms it into a generated fake member of a dataset; for example, maybe it turns it into a picture of a face. The discriminator recieves either a real member of a dataset, or a fake one made by the generator, and it predicts the probability that the input is real. To train this joint network, the generator tries to maximize the discriminator's predictions on its fake inputs, and the discriminator tries to minimize those predictions and maximize predictions on the real inputs. Hence adversarial.

Answer 83

Creating new data, or new fake members of a dataset, such as images or videos Transferring aspects of a dataset onto another: making a video of a horse look like a zebra, making a photo in the style of a certain artist, turning a rough sketch of an object into a much more detailed sketch, deep fakes, etc

Answer 84

1. Get the data 2. Clean and explore it in preparation for modeling 3. Train/validate a model 4. Deploy it 5. *Monitor and update it*: check the input data doesn't drift too much, and that predictions remain good, etc

Answer 85

Applying batch normalization to a layer simply means normalizing the layer’s outputs to have mean 0 and std 1, by subtracting the batch mean and dividing by the batch variance. So we’re normalizing with respect to the current batch, not the whole dataset. So similar to how we normalize the inputs to a model, we can also normalize the inputs to layer n+1 by applying batch normalization to layer n. It’s helpful to normalize some layers within the NN, not just normalize the inputs, because in the same way that the consistency of inputs to a network helps it learn, consistent inputs to any given layer help it learn more easily, quickly, and consistently. Any layer can be thought of as “the input layer in the remaining sub-network”, and having consistent inputs to that sub-network will be helpful!

Answer 86

Basically how it's explained: subtract the batch's mean and divide by its variance. The only deviation from this is that we actually add a small epsilon to the variance in practice. This is partially to avoid a variance of zero, and partially because we’re really trying to estimate overall population variance, which is typically a little higher than a batch’s variance.

Answer 87

The primary purpose and benefit of batch norm is faster training (which could potentially allow for more complex models, or smaller learning rates, etc). A possible secondary benefit is thus that maybe we can get better accuracies. There are lots of other potential small benefits (very light regularization, potentially allowing for a wider range of activations, weight initializations are less important, can help with vanishing gradients) that probably aren't as key.

Answer 88

The gamma parameter is a pseudo-regularization tool for xgboost. It represents the minimum amount of reduction in loss that is required for a node in a decision tree to do a certain split. So if a split doesn't help enough, it won't happen. Normal regularization adds a penalty to the optimization function based on the model's complexity, whereas this parameter simply stops expanding the model if the expansion isn't helpful enough. They both achieve similar goals of limiting model complexity to hopefully combat overfitting. There do exist actual regularization terms for the models, but they seem to be less commonly used, perhaps because gamma is intuitive whereas regularizing a weirdly-parameterized decision tree model is not.

Answer 89

The xgboost library is an ML library for training models that are ensembles of decision trees using gradient boosting. The implementation in the library contains many optimizations, making it very fast and effective, hence it's popularity throughout the ML world. Creating models with xgboost is simple: its interface is very similar to sklearn for example. It was made by CMU professor Tianqi Chen!

Answer 90

Boosting is of course a technique for training an ensemble model where each model is trained sequentially, and models try specifically to correct the errors of past models. As a first note on xgboost specifically: rather than each model predicting a probability if we're doing classification, or predicting the actual outcome if we're doing regression, each tree predicts an arbitrary scalar score. So whether we're doing classification or regression, the output of a single tree is an arbitrary scalar in (-inf,inf). Then for either, the prediction of the overall model is the ***sum*** of the scalars for all these trees, rather than the average. The rest of the solution builds on summing rather than averaging. Then in gradient boosting specifically, **tree i tries to predict the negative of the residual of the model formed by trees 0 to i-1.** An intuitive explanation of why this works is basically model i is trying to predict for itself the residual of the composite model formed by models 0 to n-1, and then model i outputs the negative of that residual to correct it and make the predicted residual zero. In other words, model i is, intuitively, trying to predict the shared error of all previous models so that it can correct it. I don't know why the word 'gradient' is present. All that might not be 100% surgically accurate in all cases, but I do think it captures the big ideas of how the implementation works and the intuition behind it, Anything beyond that is pretty complicated, and hopefully not necessary. https: //machinelearningmastery.com/gentle-introduction-xgboost-applied-machine-learning/ https: //xgboost.readthedocs.io/en/latest/tutorials/model.html

Answer 91

Suppose we're using it for sentence/phrase/paragraph embeddings specifically, getting it from the embedding of the start token. We can use this for search engines: get an embedding of the text from every page on the internet, and get an embedding for the phrase the user input to the search engine, and return pages whose embeddings are similar to the query's embeddings

Answer 92

Of course because it achieves state-of-the-art results on many NLP tasks that use a language model, but also because it *makes transfer learning for NLP very easy*, similar to how it has been in the past for computer vision. BERT is a big, downloadable pre-trained model trained on gigantic sets of data (all of Wikipedia or something like that), and you can leverage that general understanding of the english language to make great task-specific word embeddings, sentence embeddings, or whatever, *without having tons of data yourself.*

Answer 93

Input your documents to BERT and get a sentence embedding for each, then train a few additional layers to predict your outcome variable based on those embeddings. If you have lots of data you could also fine-tune BERT itself.

Answer 94

BERT is a language model that takes as input a phrase and returns context-dependent word embeddings for each of the words, as well as a context-dependent embedding for start and end tokens which are placed at the beginning and end of the word. ("Context dependant word embeddings" is how I think about it.) "Base" embeddings are size 768; "large" embeddings are size 1024. "Context dependent" meaning, for example, the embedding for 'trump' will be different if it's in "Donald Trump" vs if it's in "I'll trump you." BERT is a technology based on transformers and self-attention.

Answer 95

When trying to find a context-dependent embedding for a particular word in the input phrase, it will figure out what other words in the phrase it should have its attention on based on which are relevant to this word. It's self attention because it's referencing within the original input sequence, rather than in say machine translation where you're keeping attention on places in the input phrase while creating a word in the output phrase. This is how it uses context. Say you're embedding the word "blue": in the phrase "the blue sky" you might your attention on 'sky', but in the phrase "I feel blue" you'll probably focus on the word feel, and get a very different embedding that reflects the different meaning of the word in the new context. Another example is "coreference resolution": in the phrase "I saw James and threw the ball to him", when you're embedding the word 'him', the model will hopefully have attention on the word James because it's figuring out what 'him' refers to.

Answer 96

Something like "I know that BERT essentially creates context-dependent word embeddings for each word in an input phrase, as well as for additional start and end tokens, and this is in part based on self attention...expand a bit on self attention... but it's been well over a year since I really needed to think about BERT as something other than a black box that creates good sentence embeddings, so I haven't studied up on transformers and such much recently and can't speak much to them. I'll be taking advanced NLP coursework this year though, so I'm excited to refresh myself! I'm also familiar with how BERT's outputs an be used to create sentence embeddings, useful for tasks like classification...

Answer 97

SBERT is essentially a fine-tuned version of BERT that pools word embeddings to create good sentence embeddings. For a given input phrase, BERT's output is an embedding for each word, and the start and end tokens. These can be "pooled" to make sentence embeddings: one common option is simply to output the embedding of the start token as your sentence embeddings, and another is to take the average of all the embeddings. SBERT automatically does one of these based on the version (so its output on a given phrase is a single sentence embedding vector), and it has been fine-tuned to be good at this specifically.

Answer 98

You have SBERT embed two sentences, then use something simple like cosine similarity to calculate the sentences' similarity based on the sentence embeddings, and then you compare this to a label you have between 0 and 1 showing how similar they are.

Answer 99

It can handle NaNs, which is extremely useful and something NNs can't do It has lots of explainability and feature-importance tooling you can quickly use to get a sense of what's going on

Deep Learning, xgb, BERT COPY Flashcards

(127 cards)