Course Overview

Contents

Course Overview#

Warning

These notes will be updated throughout the semester. Please check back regularly!

Course information#

Section: PHIL408F/PHPE408J
Prerequisites: No prior programming experience necessary.
Required materials: Only a working laptop/computer is needed! Book chapters, journal articles, and software are available to all students on the course website.
Meetings: Tuesdays and Thursdays from 12:30pm - 1:45pm
Location: ASY 1213

Instructor information#

Instructor: Eric Pacuit
Email: epacuit@umd.edu
Website: pacuit.org

Teaching Assistant: Justin Helms
Email: jhelms@umd.edu
Website: philosophy.umd.edu/directory/justin-helms

Schedule#

Week	Date	Topic	Reading
1	1/28	Introduction, Introduction to Python Programming slides	Syllabus, Chollet, Chapter 1, Getting Started Notes: installation, jupyter, colab, github
	1/30	Introduction to Python Programming	Python essentials, Tutorial 1
2	2/4	Introduction to Python Programming	Tutorial 1, Tutorial 2
	2/6	Introduction to Python Programming	Tutorial 2, Tutorial 3
3	2/11	First Steps in Machine Learning	Tutorial 3, numpy
	2/13	First Steps in Machine Learning	numpy, Sections 2.1-2.3 Chollet
5	2/18	Linear Classification	linear classification, linear classification algorithms, tutorial4
	2/20	Linear Classification	linear classification, linear classification algorithms
5	2/25	Linear Classification	linear classification algorithms, Chollet Section 2.4, tutorial5
	2/27	No Lecture: Work on Tutorial 5	tutorial5
6	3/4	Introduction to Gradient Descent	Chollet Section 2.4, gradient descent
	3/6	Introduction to Gradient Descent	Chollet Section 2.4, gradient descent
7	3/11	Non-Linear Classification	gradient descent, non-linear classification, binary cross entropy
	3/13	Non-Linear Classification	binary cross entropy, example: classifying movie reviews
8	3/18	No Class: Spring Break
	3/20	No Class: Spring Break
9	3/25	Classification Example	Chollet Sections 4.1-4.2, example: classifying movie reviews, example: multiclass classification, example: classifying digits
	3/27	Classification Example	Chollet Sections 4.1-4.2, example: classifying movie reviews, example: multiclass classification, example: classifying digits
10	4/1	Regression Problems	Chollet Section 4.3, introduction to regression, example: predicting housing prices
	4/3	Image Classification	Chollet Chapter 8, convolution neural networks
11	4/8	Image Classification	Chollet Chapter 8, convolution neural networks, example: classifying dogs vs. cats images, overfitting
	4/10	Image Classification	Chollet Chapter 8, convolution neural networks, example: classifying dogs vs. cats images, overfitting
11	4/15	Fine-Tuning Models	Chollet Chapter 8, using pretrained models, gpu vs. cpu
	4/17	Introduction to Language Processing	encoding text
12	4/22	Recurrent Neural Nets	Chollet Chapter 10, introduction to RNN
	4/24	Encoding Text	Chollet Chapter 11, (word encodings)[word-encodings], embeddings(embeddings), predefined word embeddings
13	4/29	Introduction to Generative Machine Learning	introduction to self-attention
	5/1	Introduction to Generative Machine Learning	introduction to self-attention, mini gpt
14	5/6	Introduction to Generative Machine Learning	introduction to self-attention, mini gpt
	5/8	Introduction to Generative Machine Learning	fine tuning GPT-2: preprocessing, fine tuning GPT-2, slides
14	5/13	Lab	final project