Scribd
Upload
141 views

Syllabus

This document outlines a course on deep learning. The course is titled "Deep Learning" and is 3 credits. It aims to present mathematical, statistical and computational challenges of building neural networks, introduce techniques for training neural networks, dimensionality reduction techniques, and designing and deploying deep learning models. The course contains 5 units covering introduction to machine learning and neural networks, deep networks, dimensionality reduction, optimization and generalization, and applications of deep learning. It has 45 total periods and outcomes include understanding deep learning principles and capabilities, analyzing datasets for neural network solutions, realigning high dimensional data, and designing TensorFlow solutions for classification problems.

Uploaded by

K.P.Revathi Asst prof - IT Dept
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
141 views

Syllabus

This document outlines a course on deep learning. The course is titled "Deep Learning" and is 3 credits. It aims to present mathematical, statistical and computational challenges of building neural networks, introduce techniques for training neural networks, dimensionality reduction techniques, and designing and deploying deep learning models. The course contains 5 units covering introduction to machine learning and neural networks, deep networks, dimensionality reduction, optimization and generalization, and applications of deep learning. It has 45 total periods and outcomes include understanding deep learning principles and capabilities, analyzing datasets for neural network solutions, realigning high dimensional data, and designing TensorFlow solutions for classification problems.

Uploaded by

K.P.Revathi Asst prof - IT Dept
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 2

Course Code Course Title Periods per week

Credits
L T P R
191AIC701T DEEP LEARNING
3 0 0 0 3

PREREQUISITES:
Nil

COURSE OBJECTIVES:
To present the mathematical, statistical and computational challenges of building neural
1.
Networks
2. To introduce techniques used for training neural networks
3. To introduce dimensionality reduction techniques
4. To enable the students to compare modeling aspects of various neural network architectures
optimization
5. To enable design and deployment of deep learning models for machine learning problems

UNIT TITLE PERIODS


1 INTRODUCTION 9
Introduction to machine learning- Linear models (SVMs and Perceptron, logistic regression)- Intro to Neural
Nets: What a shallow network computes- Training a network: loss functions, back propagation and stochastic
gradient descent- Neural networks as universal function approximates

UNIT TITLE PERIODS


2 DEEP NETWORKS 9
History of Deep Learning- A Probabilistic Theory of Deep Learning- Backpropagation and regularization, batch
normalization- VC Dimension and Neural Nets-Deep Vs Shallow Networks Convolutional Networks- Generative
Adversarial Networks (GAN), Semi-supervised Learning
UNIT TITLE PERIODS
3 DIMENTIONALITY REDUCTION 9
Linear (PCA, LDA) and manifolds, metric learning - Auto encoders and dimensionality reduction in networks -
Introduction to Convnet - Architectures – AlexNet, VGG, Inception, ResNet - Training a Convnet: weights
initialization, batch normalization, hyper parameter optimization
UNIT TITLE PERIODS
4 OPTIMIZATION AND GENERALIZATION 9
Optimization in deep learning– Non-convex optimization for deep networks- Stochastic Optimization
Generalization in neural networks- Spatial Transformer Networks- Recurrent networks, LSTM - Recurrent Neural
Network Language Models- Word-Level RNNs & Deep Reinforcement Learning - Computational & Artificial
Neuroscience
UNIT TITLE PERIODS
5 APPLICATIONS AND CASE STUDY OF DEEP LEARNING 9
Images segmentation – Object Detection – Automatic Image Captioning – Image generation with Generative
adversarial networks – Video to Text with LSTM models – Attention models for Computer Vision – Case Study:
Named Entity Recognition – Opinion Mining using Recurrent Neural Networks – Parsing and Sentiment Analysis
using Recursive Neural Networks – Sentence Classification using Convolutional Neural Networks – Dialogue
Generation with LSTMs.

TOTAL PERIODS: 45
COURSE OUTCOMES:
Upon completion of this course, student will be able
CO1: Able to understand the principles of deep learning and its capabilities
CO2: Able to analyze the given dataset for designing a neural network based solution
CO3: Realign high dimensional data using reduction techniques
CO4: Able to design and deploy simple TensorFlow-based deep learning solutions to classification problems
CO5: Able to carry out design and implementation of deep learning models for signal/image processing
applications

TEXT BOOKS:
1. Ian J. Good fellow, Yoshua Bengio, Aaron Courville, “Deep Learning”, MIT Press, 2017.

2. Francois Chollet, “Deep Learning with Python”, Manning Publications, 2018

REFERENCE BOOKS:
1. Cosma Rohilla Shalizi, Advanced Data Analysis from an Elementary Point of View, 2015.

2. Deng & Yu, Deep Learning: Methods and Applications, Now Publishers, 2013

3. Michael Nielsen, Neural Networks and Deep Learning, Determination Press, 2015

You might also like