Syllabus
Unit 1
Foundations of Deep Learning – Introduction to Machine Learning vs Deep Learning; Biological Neuron vs Artificial Neuron; Perceptron and Multilayer Perceptron (MLP); Representation Learning; Width vs Depth of Neural Networks; Activation Functions: Sigmoid, Tanh, ReLU, Leaky ReLU, ELU, Softmax; Loss Functions: MSE, Cross-Entropy; Backpropagation Algorithm; Binary and Multiclass Classification; Weight Initialization Techniques; Overfitting and Underfitting; Regularization Techniques (L1, L2, Dropout). (15Hrs)
Unit 2
Convolutional Neural Networks Motivation for CNN; Convolution Operation and Feature Maps; Filters, Stride, Padding; Pooling Layers; Parameter Sharing; Batch Normalization; Regularization in CNN; Optimization Techniques: Gradient Descent, Stochastic Gradient Descent, Mini-batch SGD, Momentum, Nesterov Accelerated Gradient, Adagrad, Adadelta, RMSProp, Adam and AdamW; Popular CNN Architectures: AlexNet, VGGNet, ResNet, DenseNet; Applications in Image Classification and Object Detection (15Hrs)
Unit 3
Transfer Learning and Advanced CNNs
Concept of Transfer Learning; Feature Extraction vs Fine-Tuning; Pre-trained Models; Large-scale Datasets (ImageNet); Advanced Architectures: Inception, MobileNet; Vision Transformers (ViT) – Basic Concepts; Applications in Medical Imaging, Face Recognition, and Industrial AI. (10 Hrs)
Unit 4
Generative Models
Autoencoders: Undercomplete, Sparse, Denoising, Contractive; Variational Autoencoder (VAE); Generative Adversarial Networks (GAN): Architecture, Minimax Optimization, DCGAN, Conditional GAN; Applications in Image Generation and Data Augmentation. (10 Hrs)
Unit 5
Sequence Modelling and Transformers
Recurrent Neural Networks (RNN); Vanishing and Exploding Gradient Problem; Backpropagation Through Time (BPTT); Long Short-Term Memory (LSTM); Gated Recurrent Unit (GRU); Bidirectional RNN; Encoder–Decoder Architecture; Attention Mechanism; Introduction to Transformers; Applications in NLP, Time Series Forecasting, and Speech Recognition. (10 Hrs)
Text Books / References
Text Books:
- Ian Goodfellow, YoshuaBengio and Aaron Courville, Deep Learning, MIT Press, 2017.
- Josh Patterson, Adam Gibson, Deep Learning: A Practitioner’s Approach, O’Reilly Media, 2017
- Umberto Michelucci, Applied Deep Learning. A Case-based Approach to Understanding Deep Neural Networks, Apress, 2018.
- Kevin P. Murphy, Machine Learning: A Probabilistic Perspective, The MIT Press, 2012.
- EthemAlpaydin, Introduction to Machine Learning, MIT Press, Prentice Hall of India, ThirdEdition 2014.
- Giancarlo Zaccone, Md. RezaulKarim, Ahmed Menshawy Deep Learning with TensorFlow:Explore neural networks with Python, Packt Publisher, 2017.
- Antonio Gulli, Sujit Pal, Deep Learning with Keras, Packt Publishers, 2017.
- Francois Chollet, Deep Learning with Python, Manning Publications, 2017.
