1.
Deep Learning Fundamentals (1–16)
Introduction & Basics
1. What is the difference between Deep Learning and Machine Learning?
2. What are the different types of Neural Networks?
3. What is a Neural Network and Artificial Neural Network (ANN)?
4. How are biological neurons similar to Artificial Neural Networks?
5. What are Weights and Biases in Neural Networks?
6. How are weights initialized in Neural Networks?
7. What is an Activation Function and how does it work?
8. What are the different types of Activation Functions used in Deep Learning?
9. What are the different layers in a Neural Network?
Perceptrons & Network Architecture
10. What is a Perceptron or Single Layer Neural Network?
11. What is a Multilayer Perceptron (MLP) and how is it different from a Single Layer Perceptron?
12. How are the number of hidden layers and neurons selected?
13. What is the difference between Shallow Networks and Deep Networks?
14. Why are Neural Networks called Black Boxes?
15. What are Feedforward Neural Networks (FNN)?
16. Are ANN, Single Layer Perceptron and Feedforward Neural Network the same?
2. Training, Loss Functions & Optimization (17–28)
Learning Process
17. What are Forward Propagation and Backward Propagation?
18. What is the Cost Function in Deep Learning?
19. What are Binary Cross-Entropy, Categorical Cross-Entropy and Sparse Categorical Cross-
Entropy?
20. How do Neural Networks learn from data?
Gradient Descent & Optimizers
21. What is Gradient Descent and its variants?
22. Define Learning Rate in Deep Learning.
23. Difference between Batch GD, SGD and Mini-Batch GD.
24. Explain Adagrad, RMSProp and Adam Optimizers.
25. What is Momentum-Based Gradient Descent?
Gradient Problems
26. What are Vanishing and Exploding Gradient Problems?
27. What is Gradient Clipping?
Training Terminology
28. Define Epoch, Iterations and Batches.
3. Regularization & Model Improvement (29–32)
29. How to avoid Overfitting in Neural Networks?
30. What are Dropout and Early Stopping?
31. What is Data Augmentation and its techniques?
32. What is Batch Normalization?
4. Convolutional Neural Networks (CNN) & Computer Vision (33–39)
CNN Fundamentals
33. What is CNN (Convolutional Neural Network)?
34. What do you mean by Convolution?
35. What is a Kernel?
36. Define Stride.
CNN Layers
37. What is Pooling Layer and its different types?
38. What is Padding in CNN?
Computer Vision Tasks
39. What is the difference between Object Detection and Image Segmentation?
5. Recurrent Neural Networks (RNN), LSTM & GRU (40–46)
RNN Basics
40. What are Recurrent Neural Networks (RNNs) and how do they work?
41. How does Backpropagation Through Time (BPTT) work in RNN?
42. What are Vanishing and Exploding Gradient Problems in traditional RNNs?
Advanced RNN Architectures
43. What is LSTM and how does it work?
44. What are BiRNN and BiLSTM?
45. What is GRU and how does it work?
46. Difference between RNN, LSTM and GRU.
6. Transformers & Attention Mechanisms (47–53)
Transformer Fundamentals
47. What is the Transformer Model?
48. What is Attention Mechanism?
49. What are different types of Attention Mechanisms?
50. What is Positional Encoding?
51. What are Layer Normalization and Residual Connections?
52. What are Tokens and Embeddings?
53. What is an Encoder-Decoder Network in Deep Learning?
7. Autoencoders & Representation Learning (54–57)
54. What is an Autoencoder?
55. What are different types of Autoencoders?
56. What is a Variational Autoencoder (VAE)?
57. What is a Sequence-to-Sequence (Seq2Seq) Model?
8. Generative AI & GANs (58–60)
58. What is a Generative Adversarial Network (GAN)?
59. What are different types of GANs?
60. What is StyleGAN?
9. Transfer Learning & Fine-Tuning (61–62)
61. What is Transfer Learning and Fine-Tuning?
62. What is the Difference Between Transfer Learning and Fine-Tuning?