Timing: 3-5 pm PST on Tuesdays and Fridays from April 7 to April 28, 2023 (7 sessions in total)
Where: Shanahan 3465 or remotely via Zoom (link will be shared when you register)

The workshop series is designed with a focus on the practical aspects of machine learning using real-world datasets and the tools in the Python ecosystem and is targeted towards complete beginners familiar with Python.


You will learn the minimal but most useful tools for exploring datasets using pandas and then be gently introduced to neural networks. You will also learn various architectures of neural networks such as Convolution Neural Networks (CNN), Recurrent Neural Networks (RNN), and transformer-based models (used in recent language models such as chatGPT), and apply them to real-world textual and image datasets.

Please register using this Google form to save your seat. It is highly recommended to attend the workshop in person as you will be coding in groups and participating in discussions, but there is an option to join remotely via Zoom. The Zoom link and the recordings for each session will be shared with the registered participants. Please have a look at the topics to be covered below. You are free to attend some of the sessions while skipping others if you are already familiar with certain topics.

The learning material and solutions will be made available in this Github repository for each session.

1. Some familiarity with Python
2. Basics of Probability and Statistics
3. Basics of Calculus
4. Basics of Linear Algebra

Here is an optional quiz to brush up your Python skills before the workshop.

Please download and install Anaconda on your laptop ahead of the workshop.

• Introduction
• Pandas dataframes as a data structure
• Indexing and slicing data frames
• Data exploration
• Basic statistical plots using matplotlib and seaborn
• Detecting and filling missing values
• Regular expressions for text mining

You can run the notebook for this session either at or

• More on pandas - Groupby operations
• Binary classification algorithm: Logistic Regression
• Underfitting and Overfitting to the training dataset; Model cross-validation

• Neural networks: Building the intuition of the architecture and the iterative learning process
• An exercise on implementing AND and OR gates using Perceptron by trial-and-error
• Multi-Layer Perception: Forward and Backward propagation
• One hot encoding for categorical features

• Vanishing gradients and exploding gradients in deep networks
• Activation functions
• Weight Initialization
• Regularization - L1 and L2, Dropout
• Tuning other hyper-parameters such as learning rate, number of epochs, etc.
• Exploring the TensorFlow Playground
• Natural language processing (NLP) concepts: Bag Of Words (BOW) model, TF-IDF vectorizor etc.
• Application of the above concepts on IMDb dataset for training a neural network for sentiment analysis

• Image preprocessing for neural networks
• Feature extraction using convolution filters
• Convolution Neural Network architecture (CNN)
• Training a CNN model on CIFAR-10 dataset

• Recurrent Neural Networks (RNN)

• Transformer model architecture (used in models such as chatGPT)
• Mini-project: Building a spam detector using dataset from Kaggle

This page will be updated frequently with more information.