Date	Topic	Reading	Items due
week 1 (Mon: 08/24)	Introduction to Machine Learning   Lecture Slides 1
week 1 (Wed: 08/26)	Google Colab and Python Review   Day02 Notes: Google Colab + Python Refresher   Day02 Notes: Pandas Introduction   Lecture Slides 2	Reading:	In-class activity#0 (due on 08/29)
week 2 (Mon: 08/31)	Pandas Tutorial   Day03 Notes: Pandas Tutorial (continue)   Day03 Notes: Pandas Practice   Lecture Slides 3	Reading:
week 2 (Wed: 09/02)	Missing Data   Day05 Notes: Handling Missing Data   Lecture Slides 5   Notebook#1 (released on 09/02)	Reading:   isna()   notna()   any()   value_counts()   dropna()   fillna()
week 3 (Mon: 09/07)	Labor Day (university holiday; classes do not meet)
week 3 (Wed: 09/09)	k-Nearest Neighbor (kNN)   Day06 Notes: k-Nearest Neighbor using Pandas Library   Lecture Slides 6	Reading:   The relationship ML and other fields	Notebook#1 (due on 09/09)
week 4 (Mon: 09/14)	Introduction to Scikit-learn Library   kNN code using Scikit-learn Library (more efficient)   Day07 Notes: kNN code with scikit-learn   Lecture Slides 7   Notebook#2 (released on 09/14)	Reading:   sklearn   sklearn::KNeighborsClassifier   sklearn::KNeighborsRegressor
week 4 (Wed: 09/16)	Data Normalization   Day08 Notes: Data Normalization   Lecture Slides 8	Reading:   sklearn: standard scalar	In-class activity#1 kNN using scikit-learn (due on 09/28)
Week 5 (Mon: 09/21)	Weighted k-NN   Graph Plot   Cross-validation Discussion   Day09 Notes: Weighted k-NN code using sklearn   Day09 Notes: Graph Plot (take home activity due by 09/25)   Lecture Slides 9	Reading:   matplotlib: Pyplot	Notebook#2 (due on 09/21)
week 5 (Wed: 09/23)	Evaluation Metrics (Accuracy, Confusion Matrix, MAE, MSE, R2)   Evaluation Metrics on kNN Regression Coding Activity   Day10 Notes: Evaluation Metrics and Testing   Lecture Slides 10   Notebook#3 (released on 09/23)	Reading:   sklearn.metrics: accuracy_score   sklearn.metrics: confusion_matrix   sklearn.metrics: mean_absolute_error   sklearn.metrics: mean_squared_error	In-class activity#2 Graph Plot (due on 09/25)
week 6 (Mon: 09/28)	Introduction to Decision Trees   Decision trees and Entropy Calculation   Paper-based in-class Activity on Decision Trees   Day10 Notes: Entropy Calculation for Decision Trees   Lecture Slides 11	Reading:
week 6 (Wed: 09/30)	Decision Tree code using Scikit-learn Library   Day12 Notes: Decision tree code using Scikit-learn   Day12 Notes: More practice exercises using Scikit-learn   Lecture Slides 12   Notebook#4 (released on 09/30)	Reading:   sklearn: Decision Tree classifier   sklearn: train and test split   sklearn: evaluation metrics   sklearn: confusion matrix	Notebook#3 (due on 09/30)   In-class activity#3 Entropy Calculation for DT (due on 10/05)
week 7 (Mon: 10/05)	Random Forest   Day13 Notes: Random Forest   Lecture Slides 13	Reading:   sklearn: Random Forest Classifier   sklearn: Random Forest Regressor   Random Forests: Leo Breiman and Adele Cutler   Application of Random Forest: A Computer Vision paper
week 7 (Wed: 10/07)	Project#1 (released on Blackboard 03/23)   Day14 Notes: Project#1   Midterm Exam (in-class exam released on Blackboard)		Notebook#4 (due on 10/07)
week 8 (Mon: 10/12)	Fall Break (classes do not meet)
week 8 (Wed: 10/14)	Linear Classifiers   Perceptron   Lecture Slides 15	Reading:
week 9 (Mon: 10/19)	Perceptron (continued)   Perceptron Learning Algorithm   Lecture Slides 16   In-class activity (linear model, perceptron)#4   Day16 Notes: Perceptron Code (optional)	Reading:   The Perceptron: A Perceiving and Recognizing Automaton (Rosenblatt - 1957)	In-class activity#4 Linear Models (due on 10/19)
week 9 (Wed: 10/21)	Introduction to Neural Networks   Neuron Model and General Weight Learning Algorithm   Multilayer Perceptron (MLP)   Lecture Slides 18	Reading:   Multilayer Perceptron (MLP)   The Backpropgation Algorithm (Rumelhart-1985)	Project#1 (due by 10/21)
week 10 (Mon: 10/26)	PyTorch Basics   Lecture Slides 19   Day20 Notes: PyTorch Basics in-class activity	Reading:   PyTorch   PyTorch: matmul()   PyTorch: transpose()   PyTorch: nn.Linear()   PyTorch: nn.Sigmoid()   PyTorch: nn.ReLU()
week 10 (Wed: 10/28)	MLP Code using PyTorch   Lecture Slides 20   Day 21 Notes: PyTorch's Useful Functions for MLP	Reading:   PyTorch: nn.Flatten()	In-class activity#5 PyTorch Basics (due on 10/24)
Week 11 (Mon: 11/02)	MLP: Multilayer Perceptron (Modular PyTorch Implementation)   Training an MLP using PyTorch (Discussion/lecture)   Lecture Slides 21   Day 22 Notes: Building Modular MLP with PyTorch	Reading:   PyTorch: nn.Softmax()   PyTorch: nn.CrossEntropyLoss()   PyTorch: nn.MSELoss()   PyTorch: optim.SGD()   PyTorch: optim.ADAM()   PyTorch: optim.RMSprop()   PyTorch: torchvision.datasets
Week 11 (Wed: 11/04)	Training an MLP using PyTorch (implementation/coding)   Lecture Slides 22   Day 23 Notes: Training MLP using PyTorch   Notebook #5 (Released on 11/04)
Week 12 (Mon: 11/09)	Convolutional Neural Network (CNN)   Lecture Slides 23 [pdf] [powerpoint]	Reading:     Popular CNN: AlexNet (Krizevsky-2012)   Popular CNN: VGGNet (Simonyan-2015)   Popular CNN: ResNet (He-2015)	In-class activity#6 Convolution and Tensor Size (due on 11/09)
Week 12 (Wed: 11/11)	Convolutional Neural Network (CNN) (implementation/coding)   Lecture Slides 24   Day 25 Notes: Building Simple CNN using PyTorch   Day 25 Notes: Training Simple CNN using PyTorch	Reading:   Earliest CNN: LeNet (LeCunn-1988)   PyTorch: nn.Conv2d()   PyTorch: nn.Flatten()   PyTorch: nn.MaxPool2d()   PyTorch: nn.AvgPool2d()
Week 13 (Mon: 11/16)	Fine-tuning vs. Training   Fine-tuning CNNs   Lecture Slides 25   Day 26 Notes: Fine-tuning CNN using PyTorch   Project#2 (released on Blackboard 11/16)	Reading:	Notebook #5 (due on 11/16)
Week 13 (Wed: 11/18)	Recurrent Neural Network (RNN)   Lecture Slides 26a   Transformer   Lecture Slides 26b	Reading:     RNN: Serial Order (Jordan-1986)   Finding Structure in Time (Elman-1990)   LSTM: Long Short-Term Memory (Hochreiter-1997)   GRU: Gated Recurrent Unit (Hochreiter-2014)   The Unreasonable Effectiveness of Recurrent Neural Networks (RNNs)     Transformer: Attention is All You Need (2017)   The Illustrated Transformer   Harvard University NLP: The Annotated   LSTM is dead. Long Live Transformers! - Paul Dirac talk   Transformer by Hand - Anna Rahn 5 min video tutorial	extended deadline
Week 14 (Mon: 11/23)	Large Language Model (LLM)   LLM Application for NLP Tasks using PyTorch   Lecture Slides 27   Day 27 Notes: LLM for sentiment classification   Day 27 Notes: LLM for paraphrase detection   Day 27 Notes: LLM for question answering	Reading:   GPT-1 (100M parameters) - Radford et al. 2018 (OpenAI)   BERT (300M parameters) - Devlin et al. 2018   GPT-2 (1.5B parameters) - Radford et al. 2019 (OpenAI)   Megatron-LM (8.0B parameters) - Shoeybi et al. 2019 (NVidia)   T5 (11.0B parameters) - Raffel et al. 2020 (Google)   T-NLG (17.0B parameters) - Microsoft Corporation 2020 (Microsoft)   GPT-3 (175.0B parameters) - Brown et al. 2020 (OpenAI)   ChatGPT (1.5B parameters) - OpenAI 2022 (OpenAI)   Sparks of Artificial General Intelligence: Early experiments with GPT-4 - MSFR'23   Dissociating language and thought in large language models-2024   OpenAI-o1 - 2024 (OpenAI)   Is OpenAI-o1 reasoning? (ML Street Talk'24)   DeepSeek 2025 (China)   Qwen 2.5-Max 2025 (Ali Baba@China)   World Model (Jurgen Schmidhuber@NeurIPS'18)   LoRA: Low-Rank Adaptation of Large Language Models (ICLR'22)
week 14 (Wed: 11/25)	Thanksgiving Break (classes do not meet)
Week 15 (Mon: 11/30)	DayXX Notes: Dimensionality Reduction Techniques   Principle Component Analysis (PCA)   Lecture Slides XX	Reading:   sklearn: Principle Component Analysis (PCA)   sklearn: Feature Selection: SelectKBest	Project#2 (due by 11/30)
Week 15 (Wed: 12/02)	Optimization: Gradient Descent (GD), Stochastic Gradient Descent (SGD)   DayXX Notes: Loss Surface Visualization   DayXX Notes: Stochastic Gradient Descent (code)   Lecture Slides XX   Course Evaluation	Reading:   An overview of gradient descent optimization algorithms - Sebastian Ruder
Week 16 (Monday: 12/07)	Final exam (consolidated for both sections)   Monday, December 7th at 4:00 pm – 5:50 pm   SCB 0101	Reading:	In-class activity#7 LLMs (due on 12/07)   Final Exam (due by 12/07 Monday)