Neural Networks and Deep Learning.
MIT 6.S191: Introduction to Deep Learning
Fundamentals of Deep Learning of Neural Networks
Module 1- Structure of Neural Networks
Course Introduction
Neural Networks: Inspiration from the Human Brain
Introduction to perceptron
Binary Classification using Perceptron
Perceptron- Training
Multiclass Classification using Perceptrons
Working of Neuron
Input and Output of a Neural Network-I
Input and Output of a Neural Network-II
Assumptions made to Simplify Neural Networks
Parameters and Hyperparameters of Neural Netwoks
Activation Functions
Summary
Module 2- Feed Forward in Neural Networks
Introduction
Information Flow in Neural Networks- Between 2 Layers
Information Flow- Image Recognisation
Comprehensions- Count of Pixals
Learning the Dimension Weight Matrices
Feedforwatd Algorithem
Vectorizes Feedforward Implementation
Understnding Vectorizes Feedforward Implementation
Summary
Module 3- Backpogation in Neural Networks
Introduction
What Does Training a Network Mean?
Complexity of Loss Function
Comprehension- Training a neural Network
Updationg the Weight and Biases-I
Updationg the Weight and Biases-II
Updationg the Weight and Biases-III
Sigmoid Backpropagation
Updationg the Weight and Biases-IV
Updationg the Weight and Biases-V
Updationg the Weight and Biases-VI
Batch in Propagation
Training in Batches
Summary
Module 4- Modifications of Neural Network
Introduction
Regularization
Dropouts
Batch Normalisation
Introduction to Keras
Summary
Module 5- Hyperparameters Tuning in Neural Network
Introduction
Loss Function-I
Loss Function-II
Minibatch Gradient Descent
Gradient Descent-I
Gradient Descent-II
Gradient Descent-III
Gradient Descent-IV
Momentum based Methods-I
Momentum based Methods-II
Momentum based Methods-III
Dropote- Bayesian appraoch
Vanishing and Exploding Gradients
Initialisation
Summary
Introduction to Natural Language Processing (NLP)
Module 1- Introduction to NLP
Introduction
NLP: Areas of Application
Understanding Text
Text Encoding
Regular expressions: Qunatifiers-I
Regular expressions: Qunatifiers-II
Comprehensive: Regular expressions
Regular expressions: Anchors and Wildcards
Regular expressions: Charaters sets
Greedy vesus Non-greedy Search
Commonlu Used RE Functions
Regular expressions: Grouping
Regular expressions: Use Cases
Summary
Module 1- Basic Laxical Processing
Introduction
Word Frequencies and Srop Words
Tokenisation
Bag-of-Words Representation
Stemming and Lemmatisation
Final Bag-of-Words Representation
TF-IDF Representation
Building a Spam Detector -I
Building a Spam Detector -II
Summary
Module 1- Advanced Laxical Processing
Introduction
Canonacalisation
Phonetic Hashing
Edit Distance
Spell Collector-I
Spell Collector-II
Pointwise Mutual Information-I
Pointwise Mutual Information-II
Summary