Principles of Deep Learning

Introduction, Naive Bayes Classification , Logistic Regression Classification , Probabilistic Graphical
Models for Classification, Decision Trees: Theory and Algorithms : Introduction, Top-Down Decision
Tree Induction, Case Studies with C4.5 and CART, Scalable Decision Tree Construction , Incremental
Decision Tree Induction,
MODULE 3 – Rule-Based Classification (9L)
Introduction, Rule Induction, Classification Based on Association Rule Mining, Applications Instance-
Based Learning: A Survey: Introduction, Instance-Based Learning Framework, Lazy SVM Classification
, Locally Weighted Regression, Lazy Naive Bayes, Lazy Decision Trees, Rule-Based Classification,
Radial Basis Function Networks: Leveraging Neural Networks for Instance-Based Learning, Lazy
Methods for Diagnostic and Visual Classification
MODULE 4 – Support Vector Machines and Neural Networks (9L)
Support Vector Machines, Neural Networks: A Review, Fundamental Concepts, Single-Layer Neural
Network, Kernel Neural Network, Multi-Layer Feed forward Network, Deep Neural Networks,
Introduction, Generic Stream Classification Algorithms, Rare Class Stream Classification, Discrete
Attributes: The Massive Domain Scenario, Other Data Domains,
MODULE 5 - Big Data Classification (9L)
Introduction , Scale-Up on a Single Machine, Scale-Up by Parallelism, Text Classification:
Introduction, Feature Selection for Text Classification, Decision Tree Classifiers, Rule-Based
Classifiers, Probabilistic and Naive Bayes Classifiers, Linear Classifiers, Proximity-Based Classifiers,
Classification of Linked and Web Data, Meta-Algorithms for Text Classification, Leveraging Additional
Training Data, Multimedia Classification, Time Series Data Classification, Discrete Sequence
Classification, Collective Classification of Network Data, Active Learning: A Survey
TEXT BOOKS
1. Charu C. Aggarwal “Data Classification: Algorithms and Applications”, CRC Press 2015.
REFERENCE BOOKS
1. Saman K. Halgamuge, Lipo Wang (Eds.) “Classification and Clustering for Knowledge
Discovery” Springer 2015
E-BOOKS
1.
https://www.semanticscholar.org/paper/Data-Classification%3A-Algorithms-and-
Applications-Coggeshall-Klinkenberg/82076c288b729fd87050e27a74760ad5f6e164bf
MOOC
1.
https://www.coursera.org/specializations/data-mining
COURSE TITLE PRINCIPLES DEEP LEARNING CREDITS 3

COURSE CODE CAB3728 COURSE CATEGORY PC L-T-P-C-S 3-0-0-3-0
CIA 50% ESE 50%
LEARNING LEVEL BTL-3
CO COURSE OUTCOMES PO
Upon completion of this course, the students will be able to
1 Design a simple Neural Networks using Linear Perceptron. 1, 2
37
2 Design a Convolutional Neural Networks using TensorFlow. 1, 2, 3
3 Explore the Differentiable Neural Computers. 1,2,3,4
4 Explore the Deep Reinforcement Learning. 1, 2, 4, 5,7
5 Design the simple deep learning algorithms for the given applications. 1, 2, 3,5,7
MODULE 1 – THE NEURAL NETWORK (9)
Mechanics of Machine Learning , The Neuron, Linear Perceptron, Linear Neurons and Their
Limitations, Sigmoid, Feed-Forward Neural Networks, Fast-Food Problem, The Delta Rule.
MODULE 2 – CONVOLUTIONAL NEURAL NETWORKS & TENSORFLOW (9)

Neurons in Human Vision, Convolutional Layer, Convolution Networks, TensorFlow, Creating and
Manipulating TensorFlow Variables, TensorFlow Operations, Implementing an Autoencoder in
Tensor.
MODULE 3 – MEMORY AUGMENTED NEURAL NETWORKS (9)
Neural Turing Machines, Attention-Based Memory Access, Differentiable Neural Computers (DNC) -
Memory Reuse - Temporal Linking - Controller Network.
MODULE 4 – DEEP REINFORCEMENT LEARNING (9)

Deep Reinforcement Learning - Markov Decision Processes, Policy Versus Value Learning, Pole-Cart
with Policy Gradients, Q-Learning
MODULE 5 – APPLICATIONS (9)
Deep learning for Real time applications, Deep Learning Applications at the Enterprise Scale, Deep
Learning Models for Healthcare Applications.
TEXT BOOKS
Nikhil Buduma, Nicholas Locascio, “Fundamentals of Deep Learning: Designing Next-
1 Generation Machine Intelligence Algorithms”, O'Reilly Media, 2017.
REFERENCE BOOKS
1 Ian Goodfellow, YoshuaBengio, Aaron Courville, ”Deep Learning (Adaptive Computation and
Machine Learning series”, MIT Press, 2017.
EBOOK
1 http://www.deeplearningbook.org/
MOOC
1 https://www.coursera.org/learn/neural-networks-deep-learning
2 https://in.udacity.com/course/deep-learning--ud730
38

Principles of Deep Learning

Uploaded by

Principles of Deep Learning

Uploaded by

Introduction, Naive Bayes Classification , Logistic Regression Classification , Probabilistic Graphical

COURSE TITLE PRINCIPLES DEEP LEARNING CREDITS 3

MODULE 2 – CONVOLUTIONAL NEURAL NETWORKS & TENSORFLOW (9)

MODULE 4 – DEEP REINFORCEMENT LEARNING (9)

You might also like