Scribd
Upload
9 views

231AD63 Deep learning

Uploaded by

Velselvi R
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
9 views

231AD63 Deep learning

Uploaded by

Velselvi R
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 2

L T P C

231AD63 DEEP LEARNING TECHNIQUES 3 0 0 3


Programme: B.Tech. Artificial Intelligence and Data Sem: 6 Category: PC
Science
Prerequisites: – AI
Aim: To understand and need and principles of deep neural networks
Course Outcomes: The Students will be able to
CO1: Explain the basics in deep neural networks
CO2: Apply Convolution Neural Network for image processing
CO3: Outline Recurrent Neural Network and its variants for text analysis
CO4: Apply model evaluation for various applications
CO5: Demonstrate various auto encoders and related applications
CO6: Build the generative models for suitable applications
UNIT I INTRODUCTION 9
Learning Algorithms – Capacity, Overfitting and Underfitting – Hyperparameters and Validation
Sets – Estimators, Bias and Variance – Maximum Likelihood Estimation – Bayesian Statistics –
Learning Algorithms – Stochastic Gradient Descent– Challenges Motivating Deep Learnin

UNIT II DEEP FEEDFORWARD NETWORKS AND REGULARIZATION 9


Deep Feedforward Networks – Learning XOR – Gradient Based Learning – Activation
Functions and Loss Functions – Hidden Units – Neural Network architecture Design and
considerations – Backpropagation and Optimization-Regularization (Ridge)- Regularization
(Lasso)- Dropout Regularization-Batch Normalization.

UNIT III CONVOLUTIONAL NETWORKS 9


CNN Architectures – Convolution – Pooling Layers – Residual Learning and ResNet-Transfer
Learning and fine tuning Using Pre-trained ResNet Models – Recurrent and Recursive Nets –
Recurrent Neural Networks – Deep Recurrent Networks – Recursive Neural Networks-
Applications

UNIT IV DEEP LEARNING ARCHITECTURE 9


Long Short Term Memory (LSTM) Networks – Sequence Prediction – Gated Recurrent –
Encoder/Decoder Architectures – Autoencoders – Standard – Sparse – Denoising – Contractive –
Variational Autoencoders – Applications of Autoencoders

UNIT V ADVANCED DEEP LEARNING TECHNIQUES 9


Deep Belief Networks – Deep Boltzman Machine – Generative Neural Networks – GAN and its
variants – Transfer Learning – BERT – GPT – XLNet – T5 – Deep fake Technology –
Applications-Images segmentation – Object Detection – Automatic Image Captioning.

Total Periods: 45
Text Book:
1. Ian Goodfellow, Yoshua Bengio, Aaron Courville, ``Deep Learning'', MIT Press, 2016.
2. “Neural Networks and Deep Learning” by Michael Nielsen 2015
3. “Convolutional Neural Networks for Visual Recognition” by Fei-Fei Li, Andrej Karpathy, and
Justin Johnson 2016

References:
1. Salman Khan, Hossein Rahmani, Syed Afaq Ali Shah, Mohammed Bennamoun, ``A Guide to
Convolutional Neural Networks for Computer Vision'', Synthesis Lectures on Computer Vision,
Morgan & Claypool publishers, 2018.
2. Yoav Goldberg, ``Neural Network Methods for Natural Language Processing'',Synthesis
Lectures on Human Language Technologies, Morgan & Claypool publishers, 2017.
3. Francois Chollet, ``Deep Learning with Python'', Manning Publications Co, 2018.
4. Charu C. Aggarwal, ``Neural Networks and Deep Learning: A Textbook'', Springer
International Publishing, 2018.

You might also like