NEURAL NETWORKS AND DEEP LEARNING CST 395 CS 5TH SEMESTER HONORS COURSE NOTES - Dr Binu V P, 9847390760

About Me

Syllabus

Previous Year Question Papers CST 395 Neural Network and Deep Learning

Module 1 ( Basics of Machine Learning)

Overview of Machine Learning

Machine Learning Algorithm

Linear Regression

Capacity, Overfitting and Underfitting

Regularization

Hyperparameters and Validation Sets

Estimators, Bias , Variance and Consistency

Challenges In Machine Learning

Linear and Logistic Regression ( Python code)

Performance Measures

Differentiation of  sigmoid and cross entropy function

Gradient Descent, Stochastic, Batch and mini batch gradient descent

Regression with Gradient Descent

Module-2 (Neural Networks)

Introduction to Neural Networks

Application of Neural Networks

Basic Architecture- Single Layer Neural Network

Power of Function Composition- Non Linear Activation XOR

Activation Functions

Choice of activation and loss functions

Multi Layer Neural Network, Back Propagation

Back Propagation- Example

Implementation of a two layer network(XOR) with sigmoid activation function

Practical Issues in Neural Network Training

Techniques to prevent over fitting in Neural Network

Neural network and training ( additional reading)

Module-3 ( Deep Neural Network)

Deep feed forward networks

Training Deep models

Setup and Initialization

Vanishing and exploding gradient problems

Gradient Descent Strategies

Generalizing the Deep Neural Networks

Bias Variance Trade off

Generalization issues in Model Tuning and Evaluation

Penalty Based regularization-L1 and L2

Ensemble Methods

Dropout

Early Stopping

Parameter sharing and tying

Data Augmentation

Module-4 ( Convolutional Neural Network -CNN)

Introduction to CNN

Convolution Operation

Motivation

The Basic Structure of a CNN

Padding

Strides

ReLU Layer

Pooling

Fully Connected Layers

Local Response Normalization

Hierarchical Feature Engineering

Case Study-AlexNet

Module-5 ( Recurrent Neural Network)

Introduction to RNN

The Architecture of RNN

Language Modelling Example of RNN

Bidirectional Recurrent Networks

Multilayer Recurrent Networks (Deep Recurrent Network)

Recursive Neural Network

Long  Short-Term Memory- LSTM

Gated Recurrent Units-GRU

Applications of RNN

Comments

  1. Percept Rehabilitation Center7 May 2024 at 12:22

    Best Occupational Therapy Center In Uttar Pradesh | PerceptRehabilitationCenter

    Percept Rehabilitation Center is your one stop for the Best Occupational Therapy Center In Uttar Pradesh. We understand the need of finding the right care, especially for you children's. That's why we offer wide range of services which is designed to solve various needs and conditions. At Percept Rehabilitation Center we believe in the best approach to healthcare. Our team of experienced experts in varities of therapeutic interventions to help your childrens overcome challenges and achieve your goals. From motor development to speech therapy, we have the expertise to meet your needs. Our Services: Speech Therapy, Motor Development Therapy, Early Intervention, Development Therapy, Brain Gym Activities & Behavior Management. At Percept Rehabilitation Center, we are promising our customers to providing the best occupational therapy service for all ages of childrens. Whether your child is struggling with the sensory integration, behviour management or motor skills, at Percept Rehabilitation Center our expert team of occupational therapist is here to help you.

    326, first floor, near Cambridge school, Shakti Khand III, Indirapuram, Ghaziabad, Uttar Pradesh 201014

    Locate us: Percept Rehabilitation Center (Dr. Neetu Solanki -Occupational Therapist)

    Phone: 08860460038

    occupational therapy

    occupational therapy

    ReplyDelete
  2. Percept Rehabilitation Center8 May 2024 at 07:16

    Verde | Shop Premium Accessories: Ties, Cufflinks, Totes & More

    Welcome to Verde, we are an Indian brand that celebrates the joy of self- expression and embracing your unique style. Explore our consciously crafted selected of accessories, made in India. Looking for the perfect finishing touch to your outfit? We've got you covered! From best-in-class men's ties in classic blue, green, and navy to unique designer cufflinks, including dog designs in silver and gold, we offer a classy selection for every taste. Upgrade your formal wear with our premium neck ties and navy blue coat ties or add a touch of personality with our luxury and unique cufflinks. We also have the perfect gift sets with ties and pocket squares.


    HD 404, We Work DLF Forum, Cybercity, Near DLF Cyber Hub, Phase 3, Gurugram, Haryana, 122002


    +91 9717222550

    contact@verdelife.co

    ReplyDelete

Post a Comment

Popular posts from this blog

Syllabus CST 395 Neural Network and Deep Learning

Syllabus Module - 1 (Basics of Machine Learning ) Machine Learning basics - Learning algorithms - Supervised, Unsupervised, Reinforcement, overfitting, Underfitting, Hyper parameters and Validation sets, Estimators -Bias and Variance. Challenges in machine learning. Simple Linear Regression, Logistic Regression, Performance measures - Confusion matrix, Accuracy, Precision, Recall, Sensitivity, Specificity, Receiver Operating Characteristic curve( ROC), Area Under Curve(AUC). Module -2 (Neural Networks ) Introduction to neural networks -Single layer perceptrons, Multi Layer Perceptrons (MLPs), Representation Power of MLPs, Activation functions - Sigmoid, Tanh, ReLU, Softmax. Risk minimization, Loss function, Training MLPs with backpropagation, Practical issues in neural network training - The Problem of Overfitting, Vanishing and exploding gradient problems, Difficulties in convergence, Local and spurious Optima, Computational Challenges. Applications of neural networks. Module 3 (Deep
Read more

Introduction to neural networks

Image
Artificial neural networks are popular machine learning techniques that simulate the mechanism of learning in biological organisms. The human nervous system contains cells, which are referred to as neurons . The neurons are connected to one another with the use of axons and dendrites , and the connecting regions between axons and dendrites are referred to as synapses .The strengths of synaptic connections often change in response to external stimuli. This change is how learning takes place in living organisms. This biological mechanism is simulated in artificial neural networks, which contain computation units that are referred to as neurons . The computational units are connected to one another through weights, which serve the same role as the strengths of synaptic connections in biological organisms. Each input to a  neuron is scaled with a weight, which affects the function computed at that unit. The following figure shows both the biological and artificial neural networks. An artif
Read more