Machine learning Flashcards
What is AI?
AI = generic term for machine learning
Going from generic to more specialized fields, which of the following is true:
a) AI is a form of machine learning, which is a form of deep learning
b) Deep learning is a type of AI, which is a type of machine learning
c) Machine learning is a type of AI, which is a type of deep learning
d) Deep learning is a form of machine learning, which is a form of AI
d) AI → ML → deep learning
What kind of learning is artificial intelligence?
Rule-based learning
Can think of in terms of if/else or if/then statements
On what is machine learning based?
Machine learning is based on examples
Comprises training & prediction stage
Forms of learning frameworks
1) supervised (learning with a labeled training set)
2) Unsupervised (finding patterns in unlabeled data)
3) Reinforcement learning (learning based on feedback)
What do labels do?
Help to define the research question
In supervised learning, the machine…
learns functions that maps inputs to outputs
training is in the form of example inputs and desired outputs
In unsupervised learning, the machine…
learns structures within the data
-→ the goal is to discover hidden patterns and be a means toward and end
(feature learning)
ex: classifying different types of cats w/o specific characteristics of each cat type but rather the general classification of cats ; ML can then detect variability w/in the data classes
Which of the following is/are true regarding feature-engineering in deep learning and ML?
a. In deep learning there is no prior feature extraction, meaning the end result is the own representation of data
b. both standard ML and deep learning have features that are hand-crafted (ex: the distribution of white & gray matter, volumes, etc.)
c. only deep learning uses hand-crafted features
d. only standard machine learning uses hand-crafted features
e. both standard ML and deep learning have no prior feature extraction
a, d
Standard machine learning involves hand crafted features and deep learning has no prior feature extraction
What do generative models model and what are some examples?
model p(x,y) with x features and y labels
examples: Native bayes, gaussian mixture models, generative adversarial networks, etc.
What do discriminative models do and what are some examples?
Model p(y | x) w/ x features and y labels
examples: decision trees, logistic regression, neuronal networks, Gaussian processes, vector machines, etc.
On what is deep learning based? and on what does it rely?
Based on end-to-end learning
Relies on basis of artificial neural networks
Does not need prior feature extraction to come to a decision
What are the different architectures of artificial neural networks (ANN)?
- Fully connected neural networks (i.e. MLP)
- Convolutional neural networks
- Recurrent neural networks
- Generative adversarial networks
MLP structure
comprises input layer, hidden layer(s), and output layer
The input layer received inputs of different weights (w) based on node connectivity
Hidden layer performs non-linear transformation of the inputs and provides input to the output layer
What kind of learning does the MLP use? How?
Uses supervised learning in the form of backpropagation
The weight of the inputs is changed so that the error decreases = training
Learning = optimization
What are convolutional neural networks based on?
Are deep learning networks that are optimized for processing arrays (often in the form of videos or images)
Convolutional neural network layers
Convoluting
Pooling
Non-linearity
Neural networks are what kind of model?
Discriminative
How to overcome the issue of small sample size
Transfer learning (a form of data augmentation)
i.e. train models with other, previous models
How to overcome the explainability/black box issue
Can overcome the black box issue (idea that method to receive results is secret or difficult to understand) by generating heat maps based on input data
Step 1: train model & apply to test data
Step 2: generate heat map for each subject in the test set
Challenges w/ machine learning & AI
sample size, explainability, bias & confounding variables not accounted for, translation into clinical practice, reproducibility and benchmarking
