Date	Topic	Reading	Items due
week 1 (Tue: 01/30)	Introduction to Machine Learning   Day00 Notes: Introduction   Lecture Slides 1   Notebook#0 (released)
week 1 (Thu: 02/01)	Google Colab and Python Review   Day01 Notes: Python Refresher   Lecture Slides 2	Reading:	Notebook#0 (due on 02/01)
week 2 (Tue: 02/06)	Pandas Tutorial   Day02 Notes: Pandas Tutorial   Lecture Slides 3   Notebook#1 (released)	Reading:
week 2 (Thu: 02/08)	Practicing with Pandas   Day03 Notes: Pandas Practice   Lecture Slides 4	Reading:
week 3 (Tue: 02/13)	k-Nearest Neighbor (kNN)   Day04 Notes: k-Nearest Neighbor   Lecture Slides 5   Notebook#2 (released)		Notebook#1 (due on 02/13)
week 3 (Thu: 02/15)	kNN code, Missing Data and Normalization   Day05 Notes: kNN code, Missing Data and Normalization   Lecture Slides 6	Reading:   The relationship ML and other fields   isna()   notna()   any()   value_counts()   dropna()   fillna()
week 4 (Tue: 02/20)	Normalization and Weighted k Nearest Neighbor (kNN)   Day06 Notes: Normalization and Weighted k-Nearest Neighbor   Lecture Slides 7   Q1 (released on Blackboard)	Reading:   sklearn: standard scalar	Notebook#2 (due on 02/20)
week 4 (Thu: 02/22)	Weighted k-NN, Graph Plot, and Metrics   Day07 Notes: Weighted k-NN, Graph, and Metrics   Lecture Slides 8   Notebook#3 (released)	Reading:   Pandas DataFrame: sample   matplotlib: Pyplot
week 5 (Tue: 02/27)	Evaluation Metrics and Introduction to Decision Trees   Day08 Notes: Metrics and Testing   Lecture Slides 9	Reading:   sklearn.metrics: accuracy_score   sklearn.metrics: confusion_matrix   sklearn.metrics: mean_absolute_error   sklearn.metrics: mean_squared_error	Q1 (due on 02/29)   Notebook#3 (due on 02/29)
week 5 (Thu: 02/29)	Decision Trees   Lecture Slides 10   Paper-based in-class activity on decision trees	Reading:
week 6 (Tue: 03/05)	Introduction to Scikit Learn   Day10 Notes: introduction to sklearn   Video lectures on Blackboard   Day10 Notes: Decision Trees   Notebook#4 (released)	Reading:   sklearn: train and test split   sklearn: Decision Tree classifier   sklearn: k-Nearest-Neighbor Classifier   sklearn: evaluation metrics   sklearn: confusion matrix   sklearn: standard scalar
week 6 (Thu: 03/07)	Scikit Learn Practice   Day11 Notes: sklearn practice	Reading:
week 7 (Tue: 03/12)	Spring Break (no class)
week 7 (Thu: 03/14)	Spring Break (no class)
week 8 (Tue: 03/19)	Random Forests   Day12 Notes: Random Forests   Lecture Slides 11	Reading:   sklearn: Random Forest Classifier   Random Forests: Leo Breiman and Adele Cutler   Application of Random Forest: A Computer Vision research paper ICCV'2007	Notebook#4 (due on 03/19)
week 8 (Thu: 03/21)	Day13 Notes: Dimensionality Reduction Techniques   Principle Component Analysis (PCA)   Lecture Slides 12   Project#1 (released)   Day13 Notes: Project#1	Reading:   sklearn: k-Nearest-Neighbor Classifier   sklearn: k-Nearest-Neighbor Regressor   sklearn: Decision Tree Classifier   sklearn: Decision Tree Regressor   sklearn: Random Forest Classifier   sklearn: Random Forest Regressor   sklearn: Feature Selection: SelectKBest   sklearn: Principle Component Analysis (PCA)
week 9 (Tue: 03/26)	Perceptron   Perceptron Update Rule   Day14 Notes: Perceptron Code   In-class activity (linear model, perceptron)   Lecture Slides 13	Reading:   The Perceptron: A Perceiving and Recognizing Automaton (Rosenblatt - 1957)
week 9 (Thu: 03/28)	Neuron Model and Loss Surface   Lecture Slides 14   Day15 Notes: Loss Surface Visualization	Reading:
week 10 (Tue: 04/02)	Optimization: Gradient Descent, Stochastic Gradient Descent (SGD)   Lecture Slides 15   Day16 Notes: Stochastic Gradient Descent (code)	Reading:
week 10 (Thu: 04/04)	Introduction to Neural Networks   Multilayer Perceptron (MLP)   Lecture Slides 16	Reading:   Multilayer Perceptron (MLP)   The Backpropgation Algorithm (Rumelhart-1985)	Q2 (due by 04/04)   Project #1 (deadline extended now due by 04/05)
week 11 (Tue: 04/09)	PyTorch Basics   Lecture Slides 17   Day18 Notes: PyTorch Basics in-class activity   Day18 Notes: Building a very simple MLP using PyTorch	Reading:   PyTorch   PyTorch: matmul()   PyTorch: transpose()
week 11 (Thu: 04/11)	Multilayer Perceptron (MLP) - (Modular PyTorch Implementation)   Lecture Slides 18   Day 19 Notes: Building Modular MLP with PyTorch	Reading:   PyTorch: nn.Linear()   PyTorch: nn.Sigmoid()   PyTorch: nn.ReLU()   PyTorch: nn.Softmax()   PyTorch: nn.Flatten()   PyTorch: nn.CrossEntropyLoss()   PyTorch: nn.MSELoss()   PyTorch: optim.SGD()   PyTorch: optim.ADAM()   PyTorch: optim.RMSprop()   PyTorch: torchvision.datasets
week 12 (Tue: 04/16)	Convolutional Neural Network (CNN)   Lecture Slides 19	Reading:   Earliest CNN: LeNet (LeCunn-1988)
week 12 (Thu: 04/18)	Convolutional Neural Network (CNN) - (PyTorch Implementation)   Lecture Slides 20   Day 21 Notes   Notebook #5 (released)	Reading:   PyTorch: nn.Conv2d()   PyTorch: nn.Flatten()   PyTorch: nn.MaxPool2d()   PyTorch: nn.AvgPool2d()
week 13 (Tue: 04/23)	Fine-tuning vs. Training   Fine-tuning CNNs   Lecture Slides 21   Day 22 Notes	Reading:   Popular CNN: AlexNet (Krizevsky-2012)   Popular CNN: VGGNet (Simonyan-2015)   Popular CNN: ResNet (He-2015)
week 13 (Thu: 04/25)	Recurrent Neural Network (RNN)   RNN for Natural Language Processing (NLP)   Lecture Slides 22   Day 22 Notes   Project #2 (released)	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)	Notebook #5 (due by 04/25)
week 14 (Thu: 04/30)	Transformer   Lecture Slides 23	Reading:   Transformer: Attention is All You Need (2017)   The Illustrated Transformer   Harvard University NLP: The Annotated   LSTM is dead. Long Live Transformers! - Paul Dirac talk
week 14 (Tue: 05/02)	Transformer implementation with application   Lecture Slides 24   Day 24 Notes   Notebook #6 (released)	Reading:
week 15 (Tue: 05/07)	Large Language Model (LLM)   Lecture Slides 25   Day 24 Notes   Q3 (released on Blackboard)	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)
week 15 (Thu: 05/09)	Vision and Language Model (CLIP, BLIP)   Lecture Slides 26   Day 25 Notes	Reading:   Interacting with CLIP	Notebook #6 (due by 05/07)
Week 16 (Tue: 05/12)	No final exam!	Reading:	Q3 (due on 05/12)   Project #2 (due by 05/12)