neural networks and deep learning
DESCRIPTION
Neural Networks and Deep LearningTRANSCRIPT
Neural Networks and Deep Learning
Anastasiia Kornilova
● What is Neural Networks and Deep Learning
● How to train Neural Network● Unsupervised Feature Learning● Building Handwritten Digits Classifier● Tips and Tricks
Agenda
Inspired by human brainBest suitable for human brain tasks:● speech recognition● object recognition
NN and Deep Learning
How brain works?
How neural networks work?
Activation functions:
Feedforwarding
Error function
Stochastic Gradient Descent
Backpropagation
Backpopagation
1. Perform a feedforward pass, computing the activations for layers L2, L3, and so on up to the output layer .
2. For each output unit i in layer nl (the output layer), set
3. For
For each node i in layer l, set
4. Compute the desired partial derivatives, which are given as:
Autoencoder
Stacked autoencoder
1) Data visualization2) Train autoencoder3) Build classifier4 ) Enjoy!
NN for digits recognition
Optimization tips● Linear algebra libraries● Minibatch● More optimizations methods
(activation functions, dropout, dropconnect, automatization learning rates)
● GPU computing
Links● Machine Learning by Andrew Ng● Unsupervised Feature Learning and D
eep Learning tutorial● Neural Networks for Machine Learnin
g by Geoffrey Hinton● Neural Networks and Deep Learning -
free online book● Pylearn2 - framework for deep learnin
g