National Engineering College
(An Autonomous Institution Affiliated to Anna University, Chennai), Kovilpatti
M.E. – Computer Science and Engineering CURRICULUM & SYLLABUS Regulations 2019
19CT17E DEEP LEARNING L T P C QP 3 0 0 3 A
COURSE OUTCOMES Upon completion of this course, the student will be able to
CO1: Understand the basis of Machine Learning (K2)
CO2: Explore various Deep Learning Networks (K2)
CO3: Implement Convolutional and Recurrent Neural Algorithms (K3)
CO4: Analyze optimization and generalization in deep learning (K4)
CO5: Explore the deep learning applications (K3)
UNIT I MACHINE LEARNING BASICS 9
Introduction to machine learning - Linear models (SVMs and Perceptrons, logistic regression). Learning Algorithms – Capacity, Overfitting and underfitting – Hyperparameters and Validation Sets – Estimators, Bias and Variance – Maximum Likelihood Estimation – Bayesian Statistics – Supervised Learning Algorithms – Unsupervised Learning Algorithms – Stochastic Gradient Descent – Building a Machine Learning Algorithm – Challenges Motivating deep learning.
UNIT II DEEP NETWORKS 9
History of Deep Learning- A Probabilistic Theory of Deep Learning- Backpropagation and other Differentiation Algorithms – Regularization: Dataset Augumentation – Noise Robustness -Early Stopping, Bagging and Dropout - batch normalization- VC Dimension and Neural Nets-Deep Vs Shallow Networks- Convolutional Networks- Generative Adversarial Networks (GAN), Semisupervised Learning
UNIT III CONVOLUTION & RECURRENT NETWORKS 9
Convolutional Neural Networks: The Convolution Operation – Motivation – Pooling – Variants of the basic Convolution Function – Structured Outputs – Data Types – Efficient Convolution Algorithms. Recurrent Neural Networks: Bidirectional RNNs – Deep Recurrent Networks – Recursive Neural Networks.
UNIT IV 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 V CASE STUDY AND APPLICATIONS 9
Imagenet- Object Detection – Object Tracking - Audio WaveNet - Natural Language Processing
Word2Vec - Joint Detection - Face Recognition - Scene Understanding - Gathering Image
Captions.
L:45; TOTAL: 45 PERIODS
REFERENCES
1. Bengio, Yoshua, Ian J. Goodfellow, and Aaron Courville. "Deep learning." An MIT
Press book in preparation,2016.
2. Dr.Adrian Rosebrock, ―Deep Learning for Computer Vision with Python: Starter Bundle‖,
PyImage Search, 1st edition, 2017.
3. Deng & Yu, Deep Learning: Methods and Applications, Now Publishers, 2013.
4. Michael Nielsen, Neural Networks and Deep Learning, Determination Press, 2015.
- Teacher: Dr GOMATHI V