Deep Learning and Artificial Intelligence

1. Instructors

Jean Feng and Ting Ye

Module length: 2.5 days

2. Course description

This short course will provide an overview of the statistical underpinnings of Deep Learning (DL) and Artificial Intelligence (AI). The course will trace the evolution of AI models, beginning with Dense Neural Networks before progressing through Convolutional (CNN) and Recurrent (RNN) frameworks to modern Transformers, Diffusion models, and AI agents. Beyond model architecture, we will also explore the relationship between AI and statistics: how AI can advance statistical analyses and research, and conversely how statistics can advance AI.

3. Course session schedule

Wed, July 29, 11:30am-2:30pm (3h)

• 11:30 - 1:00: Lecture 1: Introduction, neural network fundamentals, and Tensorflow Playground activity – Jean
• 1:00 - 1:10: Break
• 1:10 - 1:30: Lab – Learning PyTorch - Jean
• 1:30 - 1:40: Break
• 1:40 - 2:30: Lecture 2: Optimization – Ting

Thu, July 30, 8am-2:30pm (6.5h)

• 8:05 - 9:00: Lecture 3: Recurrent neural networks (RNNs) – Jean
• 9:00 - 9:10: Break
• 9:10 - 9:50: Lab: https://colab.research.google.com/github/nyandwi/machine_learning_complete/blob/main/9_nlp_with_tensorflow/3_recurrent_neural_networks.ipynb
• 9:50 - 10:00: Break
• 10:00-11:00: Lecture 4: Attention and transformers – Jean
• 11:00 - 11:10: Break
• 11:10 - 12:00: Lab: https://colab.research.google.com/github/huggingface/education-toolkit/blob/main/03_getting-started-with-transformers.ipynb
• 12:00 - 12:30: Long Break
• 12:30 - 1:30: Lecture 5: Convolutional neural networks (CNNs) – Ting
• 1:30-1:40: Break
• 1:40 - 2:30: Lab: https://colab.research.google.com/drive/1OiwfaRqtoviONx9qGil1n3RVYpWPUDhj?usp=sharing#scrollTo=-R5siJd_MnMY

Fri, July 31, 8am-2:30pm (6.5h)

• 8:05 - 9:10: Lecture 6 + Lab: Coding a transformer from scratch https://github.com/karpathy/minGPT/tree/master – Jean
• 9:10 - 9:20: Break
• 9:20 - 10:10: Lecture 7: Large language models: pre-training and post-training – Ting
• 10:10 - 10:20: Break
• 10:20-11:00: Lab: https://colab.research.google.com/drive/1csaQKYh-quAwG_Q6Vk-y2kgQXA1kftkb?usp=sharing
• 11:00 - 11:30: Long break
• 11:30 - 12:20: Lecture 8: Diffusion models – Ting
• 12:20 - 12:30: Break
• 12:30 - 1:30: Lab: https://colab.research.google.com/github/huggingface/diffusion-models-class/blob/main/unit1/01_introduction_to_diffusers.ipynb#scrollTo=FlX4eeECD9HO
• 1:30-1:40: Break
• 1:40 - 2:10: Lecture 9: AI and statistics – Jean
• 2:10 - 2:30: General discussion