0% found this document useful (0 votes)
37 views3 pages

Machine Learning Bits Goa Handout

The document outlines a course titled 'Intro To ML and DL' offered at the Birla Institute of Technology and Science, focusing on Machine Learning, Deep Learning, and Reinforcement Learning. It includes a comprehensive course plan covering various topics such as regression, neural networks, and reinforcement learning, with an emphasis on independent learning through research. Evaluation will be based on Kaggle competitions and a final project.

Uploaded by

Yashvardhan Mote
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
0% found this document useful (0 votes)
37 views3 pages

Machine Learning Bits Goa Handout

The document outlines a course titled 'Intro To ML and DL' offered at the Birla Institute of Technology and Science, focusing on Machine Learning, Deep Learning, and Reinforcement Learning. It includes a comprehensive course plan covering various topics such as regression, neural networks, and reinforcement learning, with an emphasis on independent learning through research. Evaluation will be based on Kaggle competitions and a final project.

Uploaded by

Yashvardhan Mote
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/ 3

Birla Institute of Technology and Science, K.K.

Birla Goa Campus


Center for Technical Education
Second Semester – 2021-2022

Course Title: Intro To ML and DL

Instructors: Shreyas Bhat, Aditya Agrawal, Abhijit Deo


Mentors: Hardik Shah

Course Description:
Machine Learning is a field that is developing at a tremendous pace today. It becomes
all the more important that today’s engineers are aware of the nitty-gritty of Machine
Learning. This course aims to provide the students with an in-depth knowledge of
Machine Learning, including theoretical and practical aspects. The course will also focus
on making sure students are accustomed to learning new concepts
independently through research papers, MOOCs, and others’ understanding of
people’s code. As the field has become much more diverse than before, this course
will also discuss basic concepts of recent Deep Learning and Reinforcement Learning
methods, which will help the students pursue their journey into these fields further.

Course Prerequisites:
None
Course Plan:

Week Topic Subtopic

1 What is ML, DL, AI, RL? Intro ● Python: Lists, Tuples,


to Python Dictionaries, Conditionals,
Loops, Iterators, Functions,
Comprehensions
● Using Jupyter
notebooks, Google Colab
and GitHub
2 -Linear and Logistic Regression ● Pandas
-Exploratory Data Analysis (how to ● Matplotlib
clean data, find correlations in data) ● Box plots, correlation plots
-Feature engineering (Handling ● Introduction to scikit-learn
missing values, bad data).
3 - KNN, SVM, Naive Bayes Classifier. ● Bias-Variance Trade-off,
- Decision tree, GBM, and Random ● Validation techniques
forests. Math and statistics behind it. Metric selection
● Loss selection and
Info theory
● Bagging and Boosting
4 -Intro to OOP for ML ● Activation functions
-Neural nets ● Backpropagation
-PyTorch Computation graphs ● PyTorch Hooks

5 - Convolutional Neural Networks ● Working of CNN


- Transfer Learning ● Augmentation techniques
● Tricks while training a CNN
model.

6 - RNN ● Frequency vectors


- Intro to NLP ● Word-embeddings
- How to feed text data to machines? ● contextual Embedding

7 -Intro to Reinforcement learning ● Intro to Open-AI gym


● Frozen Lake
-State-Action concept

-Value and Policy-based methods

-Q Tables

8 Reading Research Papers ● Reading some research


papers and class discussion
End Project Description: Final projects will require students to learn some new
concepts independently and thus align with this course’s goal.
Evaluation Components:

1. Kaggle Competitions/tutorial assignments.


2. Final Project
Contact Information:

1. Shreyas Bhat – [email protected]


2. Aditya Agrawal – [email protected]
3. Abhijit Deo – [email protected]
4. Hardik Shah - [email protected]

You might also like