Gaussian processes for ML www.gaussianprocess.org/gpml/chapters/
Sent from my iPad
Month: January 2019
Some Basic Neural Networks and Applications
 Single layer perceptrons
 Multilayer perceptrons
 The deep part of deep learning.
 Convolutional Neural Networks
 Image/Video classification

 Machine translationRecurrent Neural Networks
 Language models
 Reinforcement Learning
Beginning tools:
 Pytorch
 GPU
 Caffe2
 Can run on smartphones?
Some other ML stuff.
 DeepQ Network (reinforcement learning {ML for training computers to play games},
 Sequence to sequence with attention (translation, summarization)
 Residual Networks (image recognition)
Neural Networks
Awesome at finding patterns, mapping high dimensional data. Before NN support vector machines, boosting, random forest. Perception does not actually imply intelligence.
Hebbian learning– Something positive happens you increase the positive weights.
Generative Adversarial Networks Given a random samples will generate image
Genetic Algorithm.
Single Layer Network
Activation Functions
Activation function you choose depends on the convergence of the NN
 Sigmoid is always positive and never too large. Somewhat robust to outliers.
 Rectified Linear Unit is essentially the linear function with negative rectification.
Creating Logic Gates from Single Layer Perceptrons
The decision boundaries here are arbitrary and simply represent our choice of weights. There are infinitely many weights that will satisfy our decision boundary conditions here.
Classification vs. Regression (as it applies to ML)
Generically this is determined by asking whether the estimated output is continuous or discrete. Regression representing the continuous output case say if you are fitting a line to data or discrete if you are trying to identify between say 2 colors red and blue.
How to Determine Goodness of Model
Training data is known good data. The objective function measures the difference between the target and the model (NN) output. The objective function is what we try to minimize over the weights (w). The loss function is in other mathematical language the residual sum of error squared (RSS).
Weight Updates
Where the new weight is given by: and
where
and
step size
target data
first derivative of the activation function.
input data
Getting more explicit here.
then use the chain rule:
and recall
Heaviside derivative is zero so can’t train with it. It’s useful to use the sigmoid to train and then put a threshold on (not sure how this works).
Learning Rate
Obvious problems if the learning rate is too small, never converges. If too big, miss minima.
Batch update is based on gradient descent.
 Compute the average delta weight over the whole dataset
 Update weights
 repeat
Incremental based on stochastic gradient descent.
 Compute delta w for single training example.
 update weight
 repeat until convergence.
Minibatch are subsets of the dataset. Sample dataset randomly.
Maximize the distance between the decision boundary and the data.
Decision Tree
Breaking things up into orthogonal sections. There are oblique decision trees are expensive to compute.
CNN
Sent from my iPad
Jason’s Machine Learning 101 – Google Slides
Best tutorial on ML I’ve seen yet. docs.google.com/presentation/d/1kSuQyW5DTnkVaZEjGYCkfOxvzCqGEFzWBy4e9Uedd9k/preview?imm_mid=0f9b7e&cmp=emdatanananewsltr_20171213&slide=id.g2923c61c4e_0_33
Sent from my iPad
Lie group
Lie groups for AI. Basically trying to understand how useful unitary matrices are for these problems. tacocohen.files.wordpress.com/2014/05/tsa_icml.pdf
Sent from my iPad
Education – Google AI
Google AI education link ai.google/education/
Sent from my iPad
Machine Learning for Humans, Part 4: Neural Networks & Deep Learning
Great tutorial on ML.
medium.com/machinelearningforhumans/neuralnetworksdeeplearningcdad8aeae49b
Sent from my iPad
GitHub – mattnedrich/GradientDescentExample: Example demonstrating how gradient descent may be used to solve a linear regression problem
Some simple Python example code to play around with gradient decent. github.com/mattnedrich/GradientDescentExample
Sent from my iPad
An Introduction to Gradient Descent and Linear Regression
Great into to gradient descent. Nice little examples for beginners. spin.atomicobject.com/2014/06/24/gradientdescentlinearregression/
Sent from my iPad
Introduction to Statistical Learning
Free book intro to statistical learning. wwwbcf.usc.edu/~gareth/ISL/index.html
Sent from my iPad