CS 698: Current topics in data science
Spring 2018

Instructor: Usman Roshan
Office: GITC 4207
Ph: 973-596-2872
Office hours: M: 1 to 3, W: 11:30 to 2:30
TA: Chaoran Cheng
Email: usman@njit.edu

Textbook: Not required
Grading: 30% programming assignments, 20% paper presentation, 50% project
Course Overview: This course will cover current topics in data science. We will begin with the CUDA and OpenCL languages for parallel programming on Graphics Processing Units (GPUs) followed by OpenMP for multi-core programming. While machine learning and parallel programming are separate topics we include GPU and multi-core computing in this course because of their applications in machine learning on large datasets. We will then discuss recent papers in machine learning throughout the semester such as deep learning, representation learning, optimization algorithms, algorithms for big datasets, and advance Bayesian methods. Students will present recent papers and work on parallel programming assignments. Students have the option of doing a deep learning assignment or a project of their undertaking.

Course plan:

Topic	Date	Notes
Projects		Luis: Sentiment detection from images Aradhya: Word2vec and CNN for text data Fadi: Medical image recognition with convolutional neural networks Elizabeth: Decision trees and random forests Dhara and Joseph: Sound classification Sneha and Nehal : Support vector machine and kernels Raj: Sentiment analysis from text using CNN Shih and Yucong: Facial recognition with CNN Kaizheng: Driverless car Akhil: Neural networks Akanksha: Dimensionality reduction on medical data Xuwen: Yue: Clustering Le: Deep learning Maryam and Samtha: Predicting movement of objects
Introduction to GPU computing	01/18/2018	Introduction Papers Projects Basic Unix command sheet Instructions for AFS login Some topics to start with Representation learning Geometrical and Statistical properties of systems of linear inequalities with applications in pattern recognition (Cover 1965) Approximations by superpositions of sigmoidal functions (Cybenko 1989) Approximation Capabilities of Multilayer Feedforward Networks (Hornik 1991) ImageNet classification with deep neural networks (Krizhevsky et. al. 2012) Random projections preserve margin Random projections preserve margin II For image recognition projects Python Image Library
CUDA exercise	01/26/2018	Parallel chi-square 2-df test Chi-square 2-df test in parallel on a GPU Simulated GWAS Class labels for above data Assignment 1
Basic machine learning and Python scikit-learn	02/01/2018	Basic machine learning background with Python scikit-learn Datasets Linear data Non-linear data Breast cancer (bc.train.0) (bc.test.0) Ionosphere (ion.train.0) (ion.test.0) Climate simulation (climate.train.0) (climate.test.0) Qsar (qsar.train.0) (qsar.test.0) Fifty two datasets selected from the UCI machine learning repository
OpenCL	02/08/2018	CUDA to OpenCL slides libOpenCL.so (NVIDIA library file for OpenCL code) Chi2 opencl implementation OpenCL files Assignment 2
Deep learning for lung cancer and facial image detection	02/15/2018	Fadi:PPT Papers: P1 , P2 Luisa:PPT Papers: Face expression recognition with a 2-channel convolutional neural network
Trees, forests, and sound classification	02/22/2018	Elizabeth: Decision trees, random forests, and boosting Dhara: CNN for sound classification (Paper) Python Image Library Image classification code
Word to vector representations and autoencoders	03/01/2018	Aradhya: Word2vec (Paper)
CNNs for text, multi-layer perceptrons	03/08/2018	Aradhya: CNNs for text (Papers) Multi-layer perceptrons Scikit-learn MLP code
Spring break	03/15/2018
CNNs for text, predicting motion of objects with CNNs	03/22/2018	Raj: CNNs for text Samtha: Learning Physical Intuition of Block Towers (P1) (P2) Maryam: Predicting movement of objects ( Paper ) Convolutional neural networks for image recognition Flower image classification with CNNs Assignment 3
Support vector machines, kernels, and driverless cars, mid-term review	03/29/2018	Sneha and Nehal: Support vector machines and kernels Kaizheng: Driverless cars (P1) Mid-term review sheet
Face recognition, object detection, clustering, and mid-term	04/05/2018	Shih: Deep face recognition ( P1 ) Yucong: Rich feature hierarchies for object detection ( P1 ) Yue: Clustering ensemble method based on swarm intelligence ( P1 )
	04/12/2018	Joseph: Unsupervised sound classification ( P1 ) Xuwen: SVM for cancer therapy ( P1 ) Le: Deep learning for Image Steganalysis ( P1 ) Akanksha: Principal component analysis Akhil: Neural networks
Projects	04/19/2018	Fadi: PPT Elizabeth: PPT Dhara: PPT Joseph: PPT Aradhya: PPT Raj: PPT Samtha: PPT Maryam: PPT
Projects	04/26/2018	Le Li: PPT Luisa: PPT Sneha and Nehal: PPT Kaizheng: PPT Yucong: PPT Shih: PPT Yue: PPT Xuwen: Akanksha: PPT Akhil: PPT