Deep Learning Flashcards
(15 cards)
What is deep learning?
A subset of machine learning that uses multilayered neural networks (or deep neural networks) to stimulate the complex decision making of the human brain.
How do deep learning models use unsupervised learning?
With unsupervised learning, deep learning models can extract the characteristics, features and relationships they need to make accurate outputs from raw, unstructured data. Additionally, these models can even evaluate and refine their outputs for increased precision.
What is backpropagation?
A process that uses algorithms like gradient descent to calculate errors in prediction and adjust weights and biases by moving backwards through the layers to train the model.
What technology is used with deep learning?
High performance GPUs (that can handle large volumes of calcs with lots of memory) and distributed cloud computing.
How are most deep learning apps coded (learning frameworks)
JAX, PyTorch, TensorFlow
How to auto encoders work (basic)
Autoencoders work by encoding unlabeled data into a compressed representation, and then decoding the data back into its original form.
What is the difference between plain auto encoders and variational?
Plain autoencoders were used for a variety of purposes, including reconstructing corrupted or blurry images. Variational autoencoders added the critical ability not just to reconstruct data, but also to output variations on the original data.
What to encoders do?
Encoders compress a dataset into a dense representation, arranging similar data points closer together in an abstract space
What to decoders do?
Decoders sample from the space to create something new while preserving the dataset’s most important features
What are the advantages of auto encoders?
The biggest advantage to autoencoders is the ability to handle large batches of data and show input data in a compressed form, so the most significant aspects stand out—enabling anomaly detection and classification tasks. This also speeds transmission and reduces storage requirements.
What are GANS (generative adversarial networks)
GANs are neural networks that are used both in and outside of artificial intelligence (AI) to create new data resembling the original training data. These can include images appearing to be human faces—but are generated, not taken of real people. The “adversarial” part of the name comes from the back-and-forth between the two portions of the GAN: a generator and a discriminator.
What is the generator’s role in the GAN
The generator creates something: images, video or audio and then producing an output with a twist. For example, a horse can be transformed into a zebra with some degree of accuracy. The result depends on the input and how well-trained the layers are in the generative model for this use case.
What is the discriminator’s role in the GAN
The discriminator is the adversary, where the generative result (fake image) is compared against the real images in the dataset. The discriminator tries to distinguish between the real and fake images, video or audio.
What are diffusion models?
generative models that are trained using the forward and reverse diffusion process of progressive noise-addition and denoising. Diffusion models generate data—most often images—similar to the data on which they are trained, but then overwrite the data used to train them.
What are transformer models?
Transformer models combine an encoder-decoder architecture with a text-processing mechanism and have revolutionized how language models are trained. An encoder converts raw, unannotated text into representations known as embeddings; the decoder takes these embeddings together with previous outputs of the model, and successively predicts each word in a sentence.
