Course

Module-1

Deep Neural Networks(DNN)– Convolutional Neural Network(CNN)–Recurrent Neural Network(RNN):Long-Short-Term-Memory(LSTM)-Graphbased Neural Network(GNN)

Module-2

Pre-processing:Noise Removal using deep learning algorithms-Feature Extraction-Signal Analysis:Time Series Analysis, CNNs, Auto encoders.

Module-3

Image Analysis:Transfer Learning, Attention models-Ensemble Methods for Signal and Image Analysis.

• CO1:Apply the fundamentals of deep learning.
• CO2: Apply deep learning algorithms using Matlab/Python.
• CO3: Apply deep learning models for signal analysis.
• CO4: Implement deep learning models for image analysis.

Lab Session

• Build DNN, CNN, RNN, and LSTM models using Tensor Flow or PyTorch (Python).
• Develop GNN models using PyTorch Geometric or Tensor Flow with Spektral (Python).
• Perform signal preprocessing, feature extraction, and time series analysis with CNNs and Auto encoders using Tensor Flow/Keras (Python).
• Apply transfer learning, attention models, and ensemble methods for image and signal analysis using TensorFlow or PyTorch (Python).

• Bishop C.M,“Pattern Recognition and Machine Learning”,Springer,1stEdition,2006.
• Good fellow I, Bengio Y, Courville A, & Bengio Y, “Deep learning”, Cambridge: MIT Press, 1stEdition, 2016.
• P,Ramanathan.R,“DigitalSignalandImageProcessing–TheSparseWay”,Elsevier, 1stEdition, 2012.