Scribd
Upload
9 views2 pages

DL Insem Topicwise

The document outlines the curriculum for a course on Deep Learning, covering topics such as the relationship between AI, ML, and DL, the architecture and functioning of deep learning, and the challenges and applications of deep learning. It also includes sections on neural networks, activation functions, loss functions, training algorithms, and tools used in deep learning. The document emphasizes practical applications and theoretical foundations necessary for understanding and implementing deep learning techniques.

Uploaded by

rutujagpatil2004
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
9 views2 pages

DL Insem Topicwise

The document outlines the curriculum for a course on Deep Learning, covering topics such as the relationship between AI, ML, and DL, the architecture and functioning of deep learning, and the challenges and applications of deep learning. It also includes sections on neural networks, activation functions, loss functions, training algorithms, and tools used in deep learning. The document emphasizes practical applications and theoretical foundations necessary for understanding and implementing deep learning techniques.

Uploaded by

rutujagpatil2004
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

UNIT 1 : INTRODUCTION TO DEEP LEARNING

1. AI–ML–DL Relationship & Fundamentals

a. Give co-relation between Artificial Intelligence, Machine Learning, and Deep Learning.
Compare Deep Learning with Machine Learning / Supervised and Unsupervised
Learning. [5] – (2023, 2024)

2. Definition, Working & Architecture of Deep Learning

a. How Deep Learning works in three figures explain with example? Also explain common
architectural principles of Deep Network. [5] – (2023, 2024, 2025)

b. Define Deep Learning. Explain pros and cons of using Deep Learning. [5] – (2023)

3. Bias, Variance, Overfitting & Regularization

a. Write Short Note on: Under and Over fitting regularization. [5] – (2023)

b. Explain Bias–Variance Tradeoff. [5] – (2024, 2025)

4. Limitations, Challenges & Applications

a. Explain various limitations of Machine Learning. [5] – (2023)

b. What is Deep Learning? Enlist and Explain Challenges of the Deep Learning? [5] – (2024)

c. Enlist and Explain any four real life applications of Deep Learning. [5] – (2024)

5. Industrial Tools & Platforms

a. Enlist and explain popular industrial tools used for Deep Learning. [5] – (2023, 2024,
2025)

6. CNN, RNN & Advanced Architectures

a. Explain Convolution Neural Network with diagram. [5] – (2025)

b. Short Note on LSTM and GRU networks. [5] – (2025)

c. Short note on Autoencoders and Restricted Boltzmann Machines. [5] – (2025)

UNIT 2 : NEURAL NETWORKS & DEEP MODELS

1
6. Biological Neuron, Perceptron & Feedforward Networks

a. What is Perceptron? Steps involved for training a Perceptron / Multilayer Feed Forward
Network. [5] – (2023, 2024, 2025)

7. Activation Functions

a. what is activation function? Enlist Activation functions used in Deep Neural Network.
Explain any two. [5] – (2023, 2024, 2025)

8. Loss Functions & Hyperparameters

a. Define / Enlist Loss functions used in Neural Network. Explain any two. [5] – (2023,
2024, 2025)

b. Write short note on Hyperparameters and methods of tuning them. [5] – (2023, 2025)

9. Training Algorithms & Optimization

a. Explain / Compare Backpropagation and Forward Propagation. [5] – (2023, 2024, 2025)

b. Explain Gradient Descent. Why vanishing/exploding gradient problem occurs? [5] –


(2025)

10. Tools & Libraries

a. Write short note on PyTorch and Colab. [5] – (2024)

11. NLP & Sentiment Analysis

a. Explain Sentiment Analysis and its types. [5] – (2023, 2024)

You might also like