DEEP LEARNING

 DEEP LEARNING - R25

Deep learning is a method in artificial intelligence (AI) that teaches computers to process data in a way that is inspired by the human brain. Deep learning models can recognize complex patterns in pictures, text, sounds, and other data to produce accurate insights and predictions.
Course Objectives:
1. To understand the complexity of Deep Learning algorithms and their limitations
2. To be capable of performing experiments in Deep Learning using real-world data.
Course Outcomes:
1. Implement deep learning algorithms, understand neural networks and traverse the layers of data
2. Learn topics such as convolutional neural networks, recurrent neural networks, training deep networks and high-level interfaces
3. Understand applications of Deep Learning to Computer Vision
4. Understand and analyze Applications of Deep Learning to NLP

SYLLABUS COPY

1.  THEORY SYLLABUS- CLICK HERE

2.   LAB SYLLABUS- CLICK HERE

__________________________________________________________________

           1.     website    deeplearning

           2.     Textbook    download link

              3.      NPTEL  video links clickhere

              4.       Lab Manual for reference ClickHere   

               5.      Important questions        Click here

___________________________________________________________________

Useful Video Links

UNIT 1

Topic	Video Link
1. Feed Forward Neural Networks	🔗 NPTEL – Feedforward Neural Networks and Backpropagation (Part 1)
2. Gradient Descent Algorithm	🔗 NPTEL – Gradient Descent Optimization Explained
3. Backpropagation Algorithm	🔗 NPTEL – Backpropagation Learning Example (IIT Kharagpur)
4. Unit Saturation	🔗 NPTEL – Saturation of Activation Functions (IIT KGP)
5. Vanishing Gradient Problem	🔗 NPTEL – Vanishing and Exploding Gradients
6. ReLU and Activation Function Heuristics	🔗 NPTEL – ReLU and its Variants Explained
7. Heuristics for Avoiding Bad Local Minima	🔗 NPTEL – Initialization and Local Minima (IIT Madras)
8. Heuristics for Faster Training (Momentum, etc.)	🔗 NPTEL – Optimization Algorithms: Momentum & RMSProp
9. Nesterov Accelerated Gradient Descent	🔗 NPTEL – Nesterov Accelerated Gradient Descent (CS7015)
10. Regularization in Neural Networks (L1, L2)	🔗 NPTEL – Regularization Techniques in Neural Networks
11. Dropout Regularization	🔗 NPTEL – Dropout and Overfitting Explained

UNIT 1 IMPORTANT QUESTIONS - CLICK HERE

MINOR 1 QUESTION PAPER - CLICK HERE

NOTES and Materials 

1.  FFNN

2. CNN

3. Applications of Deep Learning to NLP

4. RNNs and LSTMs in NLP

MID -1 important questions

MID 2 important Questions