Proof of Convergence of Perceptron Learning Algorithm

Perceptron Learning Algorithm

Error and Error Surfaces

Perceptrons

McCulloch Pitts Neuron, Thresholding Logic

Motivation from Biological Neurons

(Need for) Sanity

The Madness (2013-)

Beating humans at their own games (literally)

The Curious Case of Sequences

Faster, higher, stronger

From Cats to Convolutional Neural Networks

The Deep Revival

From Spring to Winter of AI

Biological Neuron

Deep Learning(CS7015): Learning Parameters: Gradient Descent

Deep Learning(CS7015): Learning Parameters: (Infeasible) guess work

Deep Learning(CS7015): A typical Supervised Machine Learning Setup

Deep Learning(CS7015): Sigmoid Neuron

Deep Learning(CS7015): Linearly Separable Boolean Functions

Deep Learning(CS7015): Representation Power of a Network of Perceptrons

Deep Learning(CS7015) :Representation Power of Multilayer Network

Information content, Entropy & cross entropy

Derivative of the activation function

Backpropagation: Pseudo code

Backpropagation: Computing Gradients w.r.t. Parameters

Backpropagation: Computing Gradients w.r.t. Hidden Units

Backpropagation: Computing Gradients w.r.t. the Output Units

Backpropagation (Intuition)

Output functions and Loss functions

Learning Paramters of Feedforward Neural Networks (Intuition)

Feedforward Neural Networks (a.k.a multilayered network of neurons)

Gradient Descent with Adaptive Learning Rate

Line Search

Tips for Adjusting Learning Rate and Momentum

Stochastic And Mini-Batch Gradient Descent

Nesterov Accelerated Gradient Descent

Bias Correction in Adam

Momentum based Gradient Descent

Contours Maps

Recap: Learning Parameters: Guess Work, Gradient Descent

Eigenvalue Decompositon

Principal Component Analysis and its Interpretations

Linear Algebra : Basic Definitions

Eigenvalues and Eigenvectors

Singular Value Decomposition

PCA : Practical Example

PCA : Interpretation 3

PCA : Interpretation 3 (Contd.)

PCA : Interpretation 2

Contractive Autoencoders

Sparse Autoencoders

Denoising Autoencoders

Regularization in autoencoders (Motivation)

Link between PCA and Autoencoders

Introduction to Autoncoders

Dropout

Ensemble Methods

Early stopping

A quick recap of training deep neural networks

Unsupervised pre-training

Better activation functions

Better initialization strategies

Batch Normalization

One-hot representations of words

Distributed Representations of words

SVD for learning word representations

SVD for learning word representations (Contd.)

Continuous bag of words model

Skip-gram model

Skip-gram model (Contd.)

Contrastive estimation

Hierarchical softmax

GloVe representations

Evaluating word representations

Relation between SVD and Word2Vec

The convolution operation

Relation between input size, output size and filter size

Convolutional Neural Networks

Convolutional Neural Networks (Contd.)

CNNs (success stories on ImageNet)

Image Classification continued (GoogLeNet and ResNet)

Visualizing patches which maximally activate a neuron

Visualizing filters of a CNN

Occlusion experiments

Finding influence of input pixels using backpropagation

Guided Backpropagation

Optimization over images

Deep Dream

Create images from embeddings

Deep Art

Fooling Deep Convolutional Neural Networks

Introduction to Encoder Decoder Models

Applications of Encoder Decoder models

Attention Mechanism

Attention Mechanism (Contd.)

Attention over images

Hierarchical Attention