← Courses Page

In this updated Pattern Recognition course, we’ll learn not only by lectures and problem sets but by diving directly into the original research papers that shaped the field. Each week, you’ll read several papers—ranging from classic template-matching methods and statistical classifiers to modern deep-learning approaches—then discuss and implement key ideas.

Our in-class sessions will be a mix of presentations, guided code walkthroughs, and Q&A. You’ll write brief critical analyses for each paper, code up core algorithms in Python (using NumPy, scikit-learn or PyTorch), and compare performance on benchmark datasets. By the end of the semester, you’ll not only master pattern-recognition techniques but also develop the critical reading and implementation skills needed to engage with cutting-edge research.

Prerequisite: Pre-Requisites: CSE 250 or EAS 230 or EAS 240 or CSE 115 or EAS 999TRCP and EAS 305 or STA 301 and STA 301 or MTH 411; Computer Science, Computer Engineering, or Bioinformatics majors only. Students must complete a mandatory advisement session with their faculty advisor.
Resources: A curated PDF reading list will be provided; expect weekly code exercises and written critiques.

Instructor Information

Course Instructor: Jue Guo

  • Research Area: Optimization for machine learning, Adversarial Learning, Continual Learning and Graph Learning
  • Interested in participating in our research? Reach to me by email.

Course Outline and Logistics

Check out the course material under lecture notes.

Course Hours: MoWe 7:00 PM – 8:20 PM

Format: Remote

Term Dates: Jun 22, 2026 – Jul 31, 2026

Course Format

This is a paper-reading seminar. Each session covers one or two papers — one foundational, one modern — tracing an arc from classical statistical pattern recognition to current research frontiers.

  • Pre-class quiz. Each session is gated by a short online quiz (~10 minutes, mix of multiple-choice and short-answer) released 48 hours before class and due 30 minutes before it starts. Questions check basic comprehension: notation, headline claims, the experimental setup, and one "did you actually read it?" detail from the paper.
  • In class. The instructor opens with a 15-min framing, then leads discussion focused on the items the quiz revealed students struggled with, followed by a deep dive into the hardest concept or derivation.
  • No exams, no formal write-ups. Comprehension is verified continuously through the quizzes; the rest of your time goes into the final project.

Schedule

Each week pairs one canonical paper with one that builds on or challenges it.

Week Date Theme & Papers
1
Statistical foundations
Jun 22 Course intro & the pattern-recognition problem before deep learning.
Cover & Hart 1967, Nearest Neighbor Pattern Classification
Jun 24 LeCun et al. 1998, Gradient-Based Learning Applied to Document Recognition (LeNet)
2
Deep representations
Jun 29 Krizhevsky et al. 2012, ImageNet Classification with Deep CNNs (AlexNet)
Jul 1 He et al. 2016, Deep Residual Learning (ResNet)
Ioffe & Szegedy 2015, Batch Normalization
3
Sequence & attention
Jul 6 Cho et al. 2014, Learning Phrase Representations with RNN Encoder-Decoder
Bahdanau et al. 2015, NMT by Jointly Learning to Align and Translate (attention)
Jul 8 Vaswani et al. 2017, Attention Is All You Need
4
Pretraining & foundation models
Jul 13 Devlin et al. 2018, BERT
Jul 15 Brown et al. 2020, GPT-3
Radford et al. 2021, CLIP
5
Robustness & adversarial PR
Jul 20 Szegedy et al. 2014, Intriguing Properties of Neural Networks
Goodfellow et al. 2015, Explaining and Harnessing Adversarial Examples (FGSM)
Jul 22 Madry et al. 2018, Towards Deep Learning Models Resistant to Adversarial Attacks (PGD)
6
Graphs & capstone
Jul 27 Kipf & Welling 2017, Semi-Supervised Classification with GCNs
Veličković et al. 2018, Graph Attention Networks (GAT)
Optional pairings: GraphSAGE, GIN — How Powerful are GNNs?
Jul 29 Final-project lightning talks — 5 min per student + Q&A.

Grading

Component Weight & Details
Pre-class quizzes 50% — 12 quizzes, drop the lowest two
In-class participation 15% — discussion quality & engagement
Final project 35% — proposal (Wk 3), draft (Wk 5), final report & demo (Wk 6)

Final Project

Pick one of three tracks:

  • Reproduce. Re-implement a paper from the syllabus on a smaller dataset and verify a key claim.
  • Extend. Propose and test a small modification to a syllabus method — new dataset, ablation, or hybrid with another paper's idea.
  • Survey. Write a 6-page critical survey of a sub-topic (max 6 papers cited), comparing methods and identifying open questions.

Artifacts: 2-page proposal (end of Wk 3) → 4-page draft for peer review (end of Wk 5) → 6-page final report + 5-min lightning talk (Wk 6).

Credits: 3

Course Hours: Lecture; TuTh 6:30 PM – 9:10 PM (Remote)

Term Dates: Jun 23 – Aug 1, 2025

Office Hours: Email to Request

Grader: Kristopher Kodweis (kkodweis@buffalo.edu)

Grader Office Hours: Email to Request

Week Session Date Paper(s) / Topic
1 Session 1 June 24, 2025 Back-Propagation (Rumelhart, Hinton & Williams, 1986)
Dropout (Srivastava et al., 2014)
1 Session 2 June 26, 2025 ReLU (Nair & Hinton, 2010)
Adam (Kingma & Ba, 2014)
2 Session 3 July 1, 2025 Batch Normalization (Ioffe & Szegedy, 2015)
RNN Encoder–Decoder (Cho et al., 2014)
2 Session 4 July 3, 2025 AlexNet (Krizhevsky et al., 2012)
VGG (Simonyan & Zisserman, 2014)
3 Session 5 July 8, 2025 ResNet (He et al., 2015)
Inception (Szegedy et al., 2015)
3 Session 6 July 10, 2025 U-Net (Ronneberger et al., 2015)
Faster R-CNN (Ren et al., 2015)
4 Session 7 July 15, 2025 YOLO (Redmon et al., 2016)
Mask R-CNN (He et al., 2017)
4 Session 8 July 17, 2025 EfficientNet (Tan & Le, 2019)
Attention Is All You Need (Vaswani et al., 2017)
5 Session 9 July 22, 2025 BERT (Devlin et al., 2018)
GPT-2 (Radford et al., 2019)
5 Session 10 July 24, 2025 RoBERTa (Liu et al., 2019)
T5 (Raffel et al., 2020)
6 Session 11 July 29, 2025 Graph Attention Networks (Veličković et al., 2018)
Deep Graph Infomax (Veličković et al., 2019)
6 Session 12 July 31, 2025 Adversarial Examples in the Physical World (Kurakin et al., 2016)
Fast is Better than Free (Wong et al., 2020)
7 Capstone August 1, 2025 Course Wrap-Up & Future Directions

Evaluation Components

Component Weight / Details
Attendance 15% (Random Attendance Check)
Exam 1 35%
Project 25%
Exam 2 25%

Note on Logistics

  • A week-ahead notice for mid-term, based on the pace of the course.
  • The logistic is subject to change based on the overall pace and the performance of the class.

Grading

The following is the outline of the grading:

Grading Rubric

This course is absolute grading, meaning no curve, as there is a certain standard we need to uphold for students to have a good knowledge of algorithm.

Percentage Letter Grade Percentage Letter Grade
95-100A 70-74C+
90-94A- 65-69C
85-89B+ 60-64C-
80-84B 55-59D
75-79B- 0-54F

AI Research Reading List

Neural Network Foundations

Computer Vision

Natural Language Processing

Graph Neural Networks

Adversarial Machine Learning

  • Adversarial Examples in the Physical World (Kurakin, Goodfellow & Bengio, 2016) – arXiv:1607.02533
  • Fast Is Better Than Free (Wong, Rice & Kolter, 2020) – arXiv:2001.03994

Continual Learning