![Collaboration Logo of Sekeh Lab, UMaine, and The Roux Institute](https://umaine.edu/ai-bootcamps/wp-content/uploads/sites/666/2023/03/logo-317x307.png)
This bootcamp is a joint effort between the Sekeh Lab at the University of Maine, and Northeastern’s Roux Institute.
Graduate students from the Sekeh Lab will present a series of tutorials, with Faculty from Universities and Principle Scientists from Industries giving talks on Deep Learning and AI.
![Mahsa Mozafarinia Photo](https://umaine.edu/ai-bootcamps/wp-content/uploads/sites/666/2023/03/IMG_20230210_132137_186-e1679081975353-317x317.jpg)
Tutorial #1: Introduction to Machine Learning (Lecture)
Instructor: Mahsa Mozafarinia
This tutorial covers basic concepts on supervised learning such as classification and regression. The students learn risk function, classifier, loss function, and optimal solutions.
![Sepideh Neshatfar Photo](https://umaine.edu/ai-bootcamps/wp-content/uploads/sites/666/2023/03/Sepideh-317x382.jpg)
Tutorial #2: Introduction to Python Programming (Practicum)
Instructor: Sepideh Neshatfar
This tutorial focuses on python programming with introduction to numpy, and SKlearn library. The SKLearn lab will teach students how to import data such as MNIST (via a Google Colab Notebook) with emphasis on how to improve classifier performance, then time for students to try their own classifiers on a separate sentiment analysis task.
![Mary Wisell Photo](https://umaine.edu/ai-bootcamps/wp-content/uploads/sites/666/2023/03/Wisell-Headshot-e1679061763608.jpg)
Tutorial #3: Introduction to Neural Network and Backpropagation (Lecture)
Instructor: Mary Wisell
This tutorial covers an introduction on multiple layer perceptron (MLP), initialization, stochastic gradient descent method, effect of learning rate on convergence, Stopping criteria, and backpropagation rule.
![Soheil Gharatappeh Photo](https://umaine.edu/ai-bootcamps/wp-content/uploads/sites/666/2023/03/Soheil-e1679061720373.jpg)
Tutorial #4: Deep Neural Network Pytorch Programming (Practicum)
Instructor: Soheil Gharatappeh
This practicum lab will have a tutorial on PyTorch and how to build feed-forward deep neural nets for the same tasks as in the Sklearn lab (with emphasis on how to improve performance). A part of the tutorial is for students to try to build their own network for the separate classification task.
![Josh Andle Photo](https://umaine.edu/ai-bootcamps/wp-content/uploads/sites/666/2023/03/Josh-317x377.jpg)
Tutorial #5: Convolutional Neural Network (CNN) Pytorch Programming (Practicum)
Instructor: Josh Andle
This practicum lab will have an introductory tutorial on training well-known Convolutional neural networks such as AlexNet, VGG, or ResNet with providing debugging tips and troubleshooting skills. A part of the tutorial is for students to try to train their model for the separate classification task. The students may try to tune a subset of CIFAR10.
![](https://umaine.edu/ai-bootcamps/wp-content/uploads/sites/666/2023/03/1675173637880-e1679079192996-317x495.jpeg)
The bootcamp includes the following talks from members of academia and industry
Talk 1: Deep Learning with Shallow Data
Speaker: Sarah Ostadabbas
Talk 2: Egocentric Audio-Visual Scene Understanding
Speaker: Chenliang Xu
Talk 3: This Looks Like That — Interpretable Deep Learning for Computer Vision and Applications in Medical Image Analysis
Speaker: Chaofan Chen
Talk 4: MultiModal ML: The Why and How of Leveraging Multiple Data Modalities
Speaker: Suren Kumar
Talk 5: Neural Networks and Inverse Problems
Speaker: Paul Hand
Talk 6: AI to AX: Artificial Intelligence to Artificial Experiences
Speaker: Nimesha Ranasinghe