T81 558:Applications of Deep Neural Networks

Section 1. Spring 2024, Monday, 2:30 PM, Location: Eads/216
Section 2. Spring 2024, Online

Course Description

Deep learning is a group of exciting new technologies for neural networks. Through a combination of advanced training techniques and neural network architectural components, it is now possible to create neural networks that can handle tabular data, images, text, and audio as both input and output. Deep learning allows a neural network to learn hierarchies of information in a way that is like the function of the human brain. This course will introduce the student to classic neural network structures, Convolution Neural Networks (CNN), Long Short-Term Memory (LSTM), Gated Recurrent Neural Networks (GRU), General Adversarial Networks (GAN) and reinforcement learning. Application of these architectures to computer vision, time series, security, natural language processing (NLP), and data generation will be covered. High Performance Computing (HPC) aspects will demonstrate how deep learning can be leveraged both on graphical processing units (GPUs), as well as grids. Focus is primarily upon the application of deep learning to problems, with some introduction to mathematical foundations. Students will use the Python programming language to implement deep learning using PyTorch. It is not necessary to know Python prior to this course; however, familiarity of at least one programming language is assumed. This course will be delivered in a hybrid format that includes both classroom and online instruction.

Objectives

Explain how neural networks (deep and otherwise) compare to other machine learning models.
Determine when a deep neural network would be a good choice for a particular problem.
Demonstrate your understanding of the material through a final project uploaded to GitHub.

Syllabus

This syllabus presents the expected class schedule, due dates, and reading assignments. Download current syllabus.

Module	Content
Module 1 Meet on 01/22/2024	Module 1: Python Preliminaries Part 1.1: Course Overview Part 1.2: Introduction to Python Part 1.3: Python Lists, Dictionaries, Sets & JSON Part 1.4: File Handling Part 1.5: Functions, Lambdas, and Map/ReducePython Preliminaries We will meet on campus this week! (first meeting)
Module 2 Week of 01/29/2024	Module 2: Python for Machine Learning Part 2.1: Introduction to Pandas for Deep Learning Part 2.2: Encoding Categorical Values in Pandas Part 2.3: Grouping, Sorting, and Shuffling Part 2.4: Using Apply and Map in Pandas Part 2.5: Feature Engineering in Padas Module 1 Program due: 01/30/2024 Icebreaker due: 01/30/2024
Module 3 Week of 02/05/2024	Module 3: PyTorch for Neural Networks Part 3.1: Deep Learning and Neural Network Introduction Part 3.2: Introduction to PyTorch Part 3.3: Encoding a Feature Vector for PyTorch Deep Learning Part 3.4: Early Stopping and Network Persistence Part 3.5: Sequences vs Classes in PyTorch Module 2: Program due: 02/06/2024
Module 4 Meet on 02/12/2024	Module 4: Training for Tabular Data Part 4.1: Using K-Fold Cross-validation with PyTorch Part 4.2: Training Schedules for PyTorch Part 4.3: Dropout Regularization Part 4.4: Batch Normalization Part 4.5: RAPIDS for Tabular Data Module 3 Program due: 02/13/2024 We will meet on campus this week! (second meeting)
Module 5 Week of 02/19/2024	Module 5: CNN and Computer Vision 5.1 Image Processing in Python 5.2 Using Convolutional Neural Networks 5.3 Using Pretrained Neural Networks 5.4 Looking at Generators and Image Augmentation 5.5 Recognizing Multiple Images with YOLO Module 4 Program due: 02/20/2024
Module 6 Week of 02/26/2024	Module 6: ChatGPT and Large Language Models 6.1: Introduction to Transformers 6.2: Accessing the ChatGPT API 6.3: LLM Memory 6.4: Introduction to Embeddings 6.5: Prompt Engineering Module 5 Program due: 02/27/2024
Module 7 Week of 03/04/2024	Module 7: Image Generative Models 7.1: Introduction to Generative AI 7.2: Generating Faces with StyleGAN3 7.3: GANS to Enhance Old Photographs Deoldify 7.4: Text to Images with StableDiffusion 7.5: Finetuning with Dreambooth Module 6 Assignment due: 03/05/2024
Module 8 Week of 03/18/2024	Module 8: Kaggle 8.1 Introduction to Kaggle 8.2 Building Ensembles with Scikit-Learn and PyTorch 8.3 How Should you Architect Your PyTorch Neural Network: Hyperparameters 8.4 Bayesian Hyperparameter Optimization for PyTorch 8.5 Current Semester's Kaggle Module 7 Assignment due: 03/19/2024
Module 9 Meet on 03/25/2024	Module 9: Facial Recognition 9.1 Detecting Faces in an Image 9.2 Detecting Facial Features 9.3 Image Augmentation 9.4 Application: Emotion Detection 9.5 Application: Blink Efficiency Module 8 Assignment due: 03/26/2024 We will meet on campus this week! (third meeting)
Module 10 Week of 04/01/2024	Module 10: Time Series in PyTorch Time Series Data Encoding for Deep Learning, PyTorch Seasonality and Trend LSTM-Based Time Series with PyTorch CNN-Based Time Series with PyTorch Predicting with Meta Prophet Module 9 Assignment due: 04/02/2024
Module 11 Week of 04/08/2024	Module 11: Natural Language Processing 11.1 Introduction to Natural Language Processing 11.2 Hugging Face Introduction 11.3 Hugging Face Tokenizers 11.4 Hugging Face Data Sets 11.5 Training a Model in Hugging Face Module 10 Assignment due: 04/09/2024
Module 12 Week of 04/15/2024	Module 12: Reinforcement Learning Kaggle Assignment due: 04/15/2024 (approx 4-6PM, due to Kaggle GMT timezone) Introduction to Gymnasium Introduction to Q-Learning Stable Baselines Q-Learning Atari Games with Stable Baselines Neural Networks Future of Reinforcement Learning
Module 13 Meet on 04/22/2024	Module 13: Deployment and Monitoring Part 13.1: Using Denoising AutoEncoders Part 13.2: Anomaly Detection Part 13.3: Model Drift and Retraining Part 13.4: Tensor Processing Units (TPUs) Part 13.5: Future Directions in Artificial Intelligence We will meet on campus this week! (fourth meeting) Final project due: 04/29/2024

Datasets

Datasets can be downloaded here

Name		Name	Last commit message	Last commit date
Latest commit History 116 Commits
assignments		assignments
install		install
.gitignore		.gitignore
CITATION.cff		CITATION.cff
LICENSE		LICENSE
README.md		README.md
citations.bib		citations.bib
copyright.md		copyright.md
intro.md		intro.md
jeffs_helpful.ipynb		jeffs_helpful.ipynb
mpg.pkl		mpg.pkl
person.json		person.json
t81_558_class_01_1_overview.ipynb		t81_558_class_01_1_overview.ipynb
t81_558_class_01_2_intro_python.ipynb		t81_558_class_01_2_intro_python.ipynb
t81_558_class_01_3_python_collections.ipynb		t81_558_class_01_3_python_collections.ipynb
t81_558_class_01_4_python_files.ipynb		t81_558_class_01_4_python_files.ipynb
t81_558_class_01_5_python_functional.ipynb		t81_558_class_01_5_python_functional.ipynb
t81_558_class_02_1_python_pandas.ipynb		t81_558_class_02_1_python_pandas.ipynb
t81_558_class_02_2_pandas_cat.ipynb		t81_558_class_02_2_pandas_cat.ipynb
t81_558_class_02_3_pandas_grouping.ipynb		t81_558_class_02_3_pandas_grouping.ipynb
t81_558_class_02_4_pandas_functional.ipynb		t81_558_class_02_4_pandas_functional.ipynb
t81_558_class_02_5_pandas_features.ipynb		t81_558_class_02_5_pandas_features.ipynb
t81_558_class_03_1_neural_net.ipynb		t81_558_class_03_1_neural_net.ipynb
t81_558_class_03_2_pytorch.ipynb		t81_558_class_03_2_pytorch.ipynb
t81_558_class_03_3_feature_encode.ipynb		t81_558_class_03_3_feature_encode.ipynb
t81_558_class_03_4_early_stop.ipynb		t81_558_class_03_4_early_stop.ipynb
t81_558_class_03_5_pytorch_class_sequence.ipynb		t81_558_class_03_5_pytorch_class_sequence.ipynb
t81_558_class_04_1_kfold.ipynb		t81_558_class_04_1_kfold.ipynb
t81_558_class_04_2_schedule.ipynb		t81_558_class_04_2_schedule.ipynb
t81_558_class_04_3_dropout.ipynb		t81_558_class_04_3_dropout.ipynb
t81_558_class_04_4_batch_norm.ipynb		t81_558_class_04_4_batch_norm.ipynb
t81_558_class_04_5_rapids.ipynb		t81_558_class_04_5_rapids.ipynb
t81_558_class_05_1_python_images.ipynb		t81_558_class_05_1_python_images.ipynb
t81_558_class_05_2_cnn.ipynb		t81_558_class_05_2_cnn.ipynb
t81_558_class_05_3_vision_transfer.ipynb		t81_558_class_05_3_vision_transfer.ipynb
t81_558_class_05_4_generators.ipynb		t81_558_class_05_4_generators.ipynb
t81_558_class_05_5_yolo.ipynb		t81_558_class_05_5_yolo.ipynb
t81_558_class_06_1_transformers.ipynb		t81_558_class_06_1_transformers.ipynb
t81_558_class_06_2_chat_gpt.ipynb		t81_558_class_06_2_chat_gpt.ipynb
t81_558_class_06_3_llm_memory.ipynb		t81_558_class_06_3_llm_memory.ipynb
t81_558_class_06_4_embedding.ipynb		t81_558_class_06_4_embedding.ipynb
t81_558_class_06_5_prompt_engineering.ipynb		t81_558_class_06_5_prompt_engineering.ipynb
t81_558_class_07_1_img_generative.ipynb		t81_558_class_07_1_img_generative.ipynb
t81_558_class_07_2_gan_intro.ipynb		t81_558_class_07_2_gan_intro.ipynb
t81_558_class_07_3_deoldify.ipynb		t81_558_class_07_3_deoldify.ipynb
t81_558_class_07_4_stable_diff.ipynb		t81_558_class_07_4_stable_diff.ipynb
t81_558_class_07_5_dream_booth.ipynb		t81_558_class_07_5_dream_booth.ipynb
t81_558_class_08_1_kaggle_intro.ipynb		t81_558_class_08_1_kaggle_intro.ipynb
t81_558_class_08_2_pytorch_ensembles.ipynb		t81_558_class_08_2_pytorch_ensembles.ipynb
t81_558_class_08_3_pytorch_hyperparameters.ipynb		t81_558_class_08_3_pytorch_hyperparameters.ipynb
t81_558_class_08_4_bayesian_hyperparameter_opt.ipynb		t81_558_class_08_4_bayesian_hyperparameter_opt.ipynb
t81_558_class_08_5_kaggle_project.ipynb		t81_558_class_08_5_kaggle_project.ipynb
t81_558_class_09_1_faces.ipynb		t81_558_class_09_1_faces.ipynb
t81_558_class_09_2_face_features.ipynb		t81_558_class_09_2_face_features.ipynb
t81_558_class_09_3_reality_augmentation.ipynb		t81_558_class_09_3_reality_augmentation.ipynb
t81_558_class_09_4_emotion.ipynb		t81_558_class_09_4_emotion.ipynb
t81_558_class_09_5_blink.ipynb		t81_558_class_09_5_blink.ipynb
t81_558_class_10_1_timeseries.ipynb		t81_558_class_10_1_timeseries.ipynb
t81_558_class_10_2_lstm.ipynb		t81_558_class_10_2_lstm.ipynb
t81_558_class_10_3_transformer_timeseries.ipynb		t81_558_class_10_3_transformer_timeseries.ipynb
t81_558_class_10_4_seasonal.ipynb		t81_558_class_10_4_seasonal.ipynb
t81_558_class_10_5_prophet.ipynb		t81_558_class_10_5_prophet.ipynb
t81_558_class_11_1_hf.ipynb		t81_558_class_11_1_hf.ipynb
t81_558_class_11_2_py_huggingface.ipynb		t81_558_class_11_2_py_huggingface.ipynb
t81_558_class_11_3_tokenizers.ipynb		t81_558_class_11_3_tokenizers.ipynb
t81_558_class_11_4_hf_datasets.ipynb		t81_558_class_11_4_hf_datasets.ipynb
t81_558_class_11_5_hf_train.ipynb		t81_558_class_11_5_hf_train.ipynb
t81_558_class_12_1_ai_gym.ipynb		t81_558_class_12_1_ai_gym.ipynb
t81_558_class_12_2_qlearningreinforcement.ipynb		t81_558_class_12_2_qlearningreinforcement.ipynb
t81_558_class_12_3_pytorch_reinforce.ipynb		t81_558_class_12_3_pytorch_reinforce.ipynb
t81_558_class_12_4_atari.ipynb		t81_558_class_12_4_atari.ipynb
t81_558_class_12_5_rl_future.ipynb		t81_558_class_12_5_rl_future.ipynb
t81_558_class_13_1_auto_encode.ipynb		t81_558_class_13_1_auto_encode.ipynb
t81_558_class_13_2_anomaly.ipynb		t81_558_class_13_2_anomaly.ipynb
t81_558_class_13_3_retrain.ipynb		t81_558_class_13_3_retrain.ipynb
t81_558_class_13_4_tpu.ipynb		t81_558_class_13_4_tpu.ipynb
t81_558_class_13_5_new_tech.ipynb		t81_558_class_13_5_new_tech.ipynb

License

jeffheaton/app_deep_learning

Folders and files

Latest commit

History