1. Home
  2. COMP
  3. COMP 457: Advanced Artificial Intelligence

COMP 457: Advanced Artificial Intelligence Report a Broken Link

Course Orientation

Zhang, A., Lipton, Z. C., Li, M., & Smola, A. J. (2023). Dive into deep learning. GitHub. https://D2L.ai
Szeliski, R. (2021). Computer vision: Algorithms and applications (2nd ed.). https://szeliski.org/Book/
Szeliski, R. (2022). Computer Vision: Algorithms and Applications, 2nd ed. download. https://szeliski.org/Book/download.php

Unit 1: Deep Learning Fundamentals

PyTorch. (2025, June 5). Introduction to PyTorch. https://docs.pytorch.org/tutorials/beginner/introyt/introyt1_tutorial.html
3Blue1Brown. (2025, September 26). Neiral networks [Video playlist]. YouTube. https://www.youtube.com/playlist?list=PLZHQObOWTQDNU6R1_67000Dx_ZCJB-3pi
Professor Bryce. (2023, October 20). Deep learning [Video Playlist]. YouTube. https://www.youtube.com/playlist?list=PLgPbN3w-ia_PeT1_c5jiLW3RJdR7853b9
Anaconda. (n.d.). Anaconda documentation. Retrieved November 28, 2025, from https://www.anaconda.com/docs/main
PyTorch. (n.d.). Get started. Retrived November 28, 2025, from https://pytorch.org/get-started/locally/
Google. (n.d.). Welcome to Colab. Retrieved November 28, 2025, from https://colab.research.google.com/

Unit 2: Natural Language Processing Fundamentals

DeepLearning.AI. (2023, January 11). A complete guide to natural language processing. Retrieved December 1, 2025, from https://www.deeplearning.ai/resources/natural-language-processing/
TORCHtext Contributors. (2024). TorchText. PyTorch. https://docs.pytorch.org/text/stable/index.html
scikit-learn devlopers. (2024). Working with text data. scikit-learn. https://scikit-learn.org/1.4/tutorial/text_analytics/working_with_text_data.html
Hugging Face. (n.d.). Introduction. Retrieved December 1, 2025, from https://huggingface.co/learn/llm-course/chapter0/1?fw=pt
Hugging Face. (n.d.). Natural language processing and large language models. Retrieved December 1, 2025, from https://huggingface.co/learn/llm-course/chapter1/2?fw=pt
PyTorch. (2025, January 24). Quickstart. Retreived December 1, 2025, from https://docs.pytorch.org/tutorials/beginner/basics/quickstart_tutorial.html
Galli, K. (2022, March 16). Complete natural language processing (NLP) tutorial in Python! (with examples) [Video]. YouTube. https://www.youtube.com/watch?v=M7SWr5xObkA

Unit 3: Computer Vision Fundamentals

Torch Contributors. (n.d.). Torchvision. PyTorch. Retrieved December 2, 2025, from https://docs.pytorch.org/vision/stable/index.html
osmr. (2024, September 18). Computer vision models on PyTorch. PyPI. https://pypi.org/project/pytorchcv/

Unit 4: Ethical Considerations

Leidner, J. L., & Plachouras, V. (2017). Ethical by design: Ethics best practices for natural language processing. Proceedings of the First ACL Workshop on Ethics in Natural Language Processing, 30–40. Association for Computational Linguistics. https://aclanthology.org/W17-1604.pdf
Waelen, R. A. (2023). The ethics of computer vision: An overview in terms of power. AI and Ethics, 4, 353–362. https://doi.org/10.1007/s43681-023-00272-x

Unit 5: Word Embedding

Stanford University School of Engineering. (2017, April 3). Lecture 3 | GloVe: Global vectors for word representation [Video]. YouTube. https://www.youtube.com/watch?v=ASn7ExxLZws
PyTorch. (2021, September 14). Word embeddings: Encoding lexical semantics. https://docs.pytorch.org/tutorials/beginner/nlp/word_embeddings_tutorial.html

Unit 6: Bidirectional Encoder Representations from Transformers

Barla, N. (2025, January 27). How to code BERT using PyTorch - Tutorial with examples. Neptune.ai. https://neptune.ai/blog/how-to-code-bert-using-pytorch-tutorial
AssemblyAI. (2021, November 27). Transformers for beginners | What they are and how do they work [Video]. YouTube. https://www.youtube.com/watch?v=_UVfwBqcnbM
3Blue1Brown. (2024, April 7). Attention in transformers, step-by-step | Deep learning chapter 6 [Video]. YouTube. https://www.youtube.com/watch?v=eMlx5fFNoYc

Unit 7: Sentiment Analysis and Natural Language Inference

There are no additional readings for this unit.

Unit 8: Advanced Natural Language Processing Applications

HuggingFace Team. (n.d.). PyTorch-transformers. PyTorch. https://pytorch.org/hub/huggingface_pytorch-transformers/
Hugging Face. (n.d.). Fine-tuning. Retrieved December 4, 2025, from https://huggingface.co/docs/transformers/training
Rogge, N. (n.d.). Fine-tuning BERT (and friends) for multi-label text classification. Google Colab. Retrieved December 4, 2025, from https://colab.research.google.com/github/NielsRogge/Transformers-Tutorials/blob/master/BERT/Fine_tuning_BERT_(and_friends)_for_multi_label_text_classification.ipynb
Kim, S., & Kang, J. (2018, November 19). Optional: Data parallelism. PyTorch. https://docs.pytorch.org/tutorials/beginner/blitz/data_parallel_tutorial.html

Unit 9: Image Processing

Torch Contributors. (n.d.). Transforming images, videos, boxes, and more. PyTorch. Retrieved December 4, 2025, from https://docs.pytorch.org/vision/stable/transforms.html
Torch Contributors. (n.d.). Operators. PyTorch. Retrieved December 4, 2025, from https://docs.pytorch.org/vision/stable/ops.html

Unit 10: Image Classification

PyTorch. (2025, September 30). Training a classifier. Retrieved December 4, 2025, from https://docs.pytorch.org/tutorials/beginner/blitz/cifar10_tutorial.html
Rosebrock, A. (2021, July 26). PyTorch image classification with pre-trained networks. PyImageSearch. https://pyimagesearch.com/2021/07/26/pytorch-image-classification-with-pre-trained-networks/

Unit 11: Object Detection

PyTorch. (2025, September 5). TorchVision object detection finetuning tutorial. Retrieved December 4, 2025, from https://docs.pytorch.org/tutorials/intermediate/torchvision_tutorial.html
Rosebrock, A. (2021, August 2). PyTorch object detection with pre-trained networks. PyImageSearch. https://pyimagesearch.com/2021/08/02/pytorch-object-detection-with-pre-trained-networks/

Unit 12: Image Segmentation

Chandhok, S. (2021, November 8). U-Net: Training image segmentation models in PyTorch. PyImageSearch. https://pyimagesearch.com/2021/11/08/u-net-training-image-segmentation-models-in-pytorch/
Matani, D. (2023, June 27). Efficient image segmentation using PyTorch: Part 1. Towards Data Science. https://towardsdatascience.com/efficient-image-segmentation-using-pytorch-part-1-89e8297a0923/
Matani, D. (2023, June 27). Efficient image segmentation using PyTorch: Part 2. Towards Data Science. https://towardsdatascience.com/efficient-image-segmentation-using-pytorch-part-2-bed68cadd7c7/
Matani, D. (2023, June 27). Efficient image segmentation using PyTorch: Part 3. Towards Data Science. https://towardsdatascience.com/efficient-image-segmentation-using-pytorch-part-3-3534cf04fb89/
Matani, D. (2023, June 27). Efficient image segmentation using PyTorch: Part 4. Towards Data Science. https://towardsdatascience.com/efficient-image-segmentation-using-pytorch-part-4-6c86da083432/
mateuszbuda. (n.d.). U-Net for brain MRI. PyTorch. Retrieved December 4, 2025, from https://pytorch.org/hub/mateuszbuda_brain-segmentation-pytorch_unet/

Unit 13: Advanced Computer Vision Applications

PyTorchVideo. (n.d.). PyTorchVideo: A deep learning library for video understanding research. Retrieved December 4, 2025, from https://pytorchvideo.org/
sgrvinod, kmario23, jasion718, & ngshya. (2020, June 2). A-PyTorch-tutorial-to-image-captioning. GitHub. https://github.com/sgrvinod/a-PyTorch-Tutorial-to-Image-Captioning

Unit 14: Generative Adversarial Networks

There are no additional readings for this unit.

Unit 15: Deep Convolutional Generative Adversarial Networks

There are no additional readings for this unit.

Assignments

Assignment 1
Khodabakhsh, H. (2019, January 8). MNIST dataset [Dataset]. Kaggle. https://www.kaggle.com/datasets/hojjatk/mnist-dataset
Assignment 2
Maas, A. L., Daly, R. E., Pham, P. T., Huang, D., Ng, A. Y., & Potts, C. (2011). Large movie review dataset [Dataset]. Stanford. https://ai.stanford.edu/~amaas/data/sentiment/
Assignment 3
Jocher, G. (2022, November 22). YOLOv5 [Version 7.0]. GitHub. https://github.com/ultralytics/yolov5