Scribd
Upload
22 views

CS-601 Machine Learning Study Guide

The document is a study guide for the CS-601 Machine Learning exam, covering key topics such as Gradient Descent, Reinforcement Learning, Neural Networks, Support Vector Machines, Data Normalization, Hypothesis Function, Regularization, Principal Component Analysis, and Autoencoders. Each section includes definitions, explanations, and important concepts related to machine learning algorithms and techniques. Additionally, it includes prompts for short notes on various frequently asked topics in the field.

Uploaded by

mitsubishisharma343
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
22 views

CS-601 Machine Learning Study Guide

The document is a study guide for the CS-601 Machine Learning exam, covering key topics such as Gradient Descent, Reinforcement Learning, Neural Networks, Support Vector Machines, Data Normalization, Hypothesis Function, Regularization, Principal Component Analysis, and Autoencoders. Each section includes definitions, explanations, and important concepts related to machine learning algorithms and techniques. Additionally, it includes prompts for short notes on various frequently asked topics in the field.

Uploaded by

mitsubishisharma343
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
You are on page 1/ 2

CS-601 (Machine Learning) - Exam Study Guide

1. Gradient Descent

- Define gradient descent in the context of optimization algorithms used in machine learning.
- What do you mean by Gradient Descent?

2. Reinforcement Learning (Q-Learning, SARSA, MDP)

- What is Reinforcement Learning (RL)? Explain its detailed concepts.


- Describe Q-learning in brief. What is SARSA algorithm? Explain this.
- Define the concept of Reinforcement Learning and its framework.
- Describe the concept of Markov Decision Process (MDP).
- Explain the Actor-Critic model. What are its advantages?

3. Neural Networks - CNN, RNN, LSTM

- Explain the architecture of a Convolutional Neural Network (CNN).


- Explain the architecture of a Recurrent Neural Network (RNN) and describe its types.
- Explain the architecture of an LSTM unit and how it handles sequential data.
- What are the different types of layers in Neural Networks (convolution, pooling, loss, dense)?
- How do pooling layers reduce the spatial dimensions of feature maps?

4. Support Vector Machines (SVM)

- Describe the concept of support vectors and their role in defining the decision boundary in SVM.
- Explain the concept and role of Support Vector Machine in detail with its application areas.

5. Data Normalization & Preprocessing

- Explain the importance of data normalization in ML for improving convergence and performance.
- What is the role of preprocessing of data in machine learning? Why is it needed?

6. Hypothesis Function

- Explain how a hypothesis function maps input features to output predictions in a machine learning
model.
- Discuss linear regression with an example. Explain the role of hypothesis function.

7. Regularization - L1 (Lasso) vs L2 (Ridge)

- Explain how L1 regularization (Lasso) and L2 regularization (Ridge) work to penalize the
magnitude of model parameters differently.

8. Principal Component Analysis (PCA)

- Explain in detail principal component analysis for dimension reduction.


- How is PCA carried out to reduce the dimensionality of data sets?

9. Autoencoders - Bottleneck Layer

- Describe the role of the bottleneck layer in autoencoders and how it captures the essential
features of the input data.

10. Short Notes (Frequently Asked)

- Write short notes on any two:


- Convex Optimization
- Linearity vs Non-Linearity
- Q-learning
- Markov Decision Process (MDP)
- Batch Normalization
- Inception Network
- Natural Language Processing (NLP)
- Scope and limitations of Machine Learning

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy