Topic
|
Date
|
Notes
|
Basic machine learning and Python scikit-learn
|
09/09/2019
|
Background
Unix and login to NJIT machines
Basic machine learning background with Python scikit-learn
Basic geometry of a linear classifier
Empirical risk minimization
Regularized risk minimization
Regularization
Support vector machine
Datasets
|
Neural networks, image classification with machine learning, and convolutions
|
09/09/2019
|
Multi-layer perceptrons
Scikit-learn MLP code
Image classification code
Python Image Library
|
Convolutional neural networks, training them with Keras
|
09/16/2019
|
Convolutional neural network
(Additional slides by Yunzhe Xue)
Flower image classification with CNNs
|
Convolutions
|
09/16/2019
|
Convolutional kernels
|
Image classification with Keras
|
09/23/2019
|
Image classification v2
CIFAR 10
CIFAR 100
STL 10
Mini ImageNet
|
| Common architectures, transposed convolutions, and U-nets
|
09/23/2019
|
Common architectures
A guide to convolution arithmetic for
deep learning
U-Net: Convolutional Networks for Biomedical
Image Segmentation
|
Generative adversarial networks (GANs)
|
09/23/2019
|
|
| Projects
|
09/30/2019
|
Course projects
- GAN to convert clinical MRI scans to research scans
- Domain adaptation by working in a common featue space
- Synthetic modalities
- Saliency maps
|
| Course projects
|
10/07/2019
|
Deep Inside Convolutional Networks:
Visualising Image Classification Models and Saliency Maps
Diagnose
like a Radiologist: Attention Guided Convolutional
Neural Network for Thorax Disease Classification
|
| Basic GAN implementation to generate hand written digits
|
10/14/2019
|
|
| Presentations
|
10/21/2019
|
Kian - Brain 2 image
Converting brain signals into
images
|
| Projects
|
10/28/2019
|
|
| Presentations
|
11/05/2019
|
Bavithra - ResNet
ResNet paper
Identity mapping paper (ResNet follow-up)
Identity mapping
|
| Projects
|
11/12/2019
|
|
| Advesarial attacks on medical AI systems
|
11/18/2019
|
Query-Efficient
Hard-label Black-box Attack: An Optimization-based Approach
Adversarial attacks on medical machine learning
Adversarial Attacks Against
Medical Deep Learning Systems
Defending Against Adversarial
Attacks Using Random Forests
Curriculum Loss: Robust
Learning and Generalization against Label Corruption
|
| Projects
|
11/25/2019
|
|
| Class cancelled due to snow
|
12/02/2019
|
|
| Presentations
|
12/09/2019
|
A Deep DUAL-PATH Network for Improved Mammogram Image
Processing by Sujoy (ppt here)
Learning from Synthetic Data: Addressing Domain Shift for
Semantic Segmentation by Triman (ppt here)
Medical Image Synthesis for Data Augmentation and
Anonymization using Generative Adversarial Networks by Stephen (ppt here)
Query-Efficient Hard-label Black-box Attack:
An Optimization-based Approach by Rohit (ppt here)
|
| Final project presentations
|
12/13/2019
|
Dual Path Convolutional Neural
Network for Student Performance Prediction by Monik (ppt here)
Final talks:
Kian
Kabilan and Triman
|
Medical AI
|
|
Brain MRI machine learning papers:
- Machine learning for brain MRIs
- Convolutional neural networks for brain MRIs
- UNets for masking images
- Public ATLAS dataset (see ATLAS)
- Other MRI machine learning studies
Cancer prediction papers:
- Cancer case and control prediction
- Cancer survival time prediction
- Cancer prediction from image data (see TCGA portal)
Ultrasound image machine learning papers:
- Ultrasound image classification
Disease risk prediction:
- Heart disease, type I and II diabetes, and other
general disease risk prediction
|