This document discusses neural networks and deep learning. It provides an agenda that covers what neural networks are, how to train a neural network, unsupervised feature learning, building a handwritten digits classifier, and tips and tricks. It describes how neural networks are inspired by the human brain and are best suited for human-like tasks such as speech and object recognition. It also outlines the processes of feedforwarding, backpropagation, autoencoders, and stacked autoencoders. Recommended links for further learning are also included.
2. Agenda
● What is Neural Networks and Deep Learning
● How to train Neural Network
● Unsupervised Feature Learning
● Building Handwritten Digits Classifier
● Tips and Tricks
3. NN and Deep Learning
Inspired by human brain
Best suitable for human brain tasks:
● speech recognition
● object recognition
13. 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
1. Compute the desired partial derivatives, which are given as:
18. Links
● Machine Learning by Andrew Ng
● Unsupervised Feature Learning and Deep
Learning tutorial
● Neural Networks for Machine Learning by
Geoffrey Hinton
● Neural Networks and Deep Learning - free
online book
● Pylearn2 - framework for deep learning