New AI Course at Columbia University, Barnard College
Deep Learning for Computer Graphics COMS BC3997Section 003 Spring 2024. This course covers neural network architectures (deep learning), related math and the fundamental theory and application of AI algorithms most popular in the field of computer graphics. Programming assignments will help students develop graphics processing unit (GPU) programming skills while implementing concepts learned in lectures and readings using deep learning APIs on a GPU cluster.
New Funding from The Vagelos Computational Science Center (CSC)
Dr. Toler-Franklin thanks the Vagelos Computational Science Center (CSC) for awarding a Computing Resource Mini-Grant of $2000.00 to support GPU compute resources for deep learning course instruction, Spring 2024.
New Funding from Activision Research
GIMLab thanks the Graphics Department of Activision Research, A Division of Microsoft Gaming, for their financial gift (Spring 2024) which will support our light measurement lab and material measurement research for appearance modeling.
Topic: AI for Cancer Detection
Department:
Computer Science
Faculty Mentor:
Corey Toler-Franklin, ct3219@columbia.edu
Ph.D. Student Mentor(s):
TBD
Terms Available:
Fall, Spring, Summer
Student Level:
Junior, Senior, Graduate
Prerequisites:
Python and/or C/C++, Machine Learning experience (a plus but not required)
Credit:
0-3 credits independent study
Stipend:
TBD
Application Requirements:
Application Deadline:
Open until filled.
Website:
Project Description:
Identifying Cancer Cells and Their Biomarker Expressions
Cell quantitation techniques are used in biomedical research to diagnose and treat cancer. Current quantitation methods are subjective and based mostly on visual impressions of stained tissue samples. This time-consuming process causes delays in therapy that reduce the effectiveness of treatments and add to patient distress. Our lab is developing computational algorithms that use deep learning to model changes in protein structure from multispectral observations of tissue. Once computed, the model can be applied to any tissue observation to detect a variety of protein markers without further spectral analysis. The deep learning model will be quantitatively evaluated on a learning dataset of cancer tumors.
Cell quantitation techniques are used in biomedical research to diagnose and treat cancer. Current quantitation methods are subjective and based mostly on visual impressions of stained tissue samples. This time-consuming process causes delays in therapy that reduce the effectiveness of treatments and add to patient distress. Our lab is developing computational algorithms that use deep learning to model changes in protein structure from multispectral observations of tissue. Once computed, the model can be applied to any tissue observation to detect a variety of protein markers without further spectral analysis. The deep learning model will be quantitatively evaluated on a learning dataset of cancer tumors.
Topic: AI for Neuroscience
Department:
Computer Science
Faculty Mentor:
Corey Toler-Franklin, ct3219@columbia.edu
Ph.D. Student Mentor(s):
TBD
Terms Available:
Fall, Spring, Summer
Student Level:
Junior, Senior, Graduate
Prerequisites:
Python and/or C/C++, Machine Learning experience (a plus but not required)
Credit:
0-3 credits independent study
Stipend:
TBD
Application Requirements:
Application Deadline:
Open until filled.
Website:
Project Description:
Deep Learning for Diagnosing and Treating Neurological Disorders
Advances in biomedical research are based upon two foundations, preclinical studies using animal models, and clinical trials with human subjects. However, translation from basic animal research to treatment of human conditions is not straightforward. Preclinical studies in animals may not replicate across labs, and a multitude of preclinical leads have failed in human clinical trials. Inspired by recent generative models for semi-supervised action recognition and probabilistic 3D human motion prediction, we are developing a system that learns animal behavior from unstructured video frames without labels or annotations. Our approach extends a generative model to incorporate adversarial inference, and transformer-based self-attention modules.
Advances in biomedical research are based upon two foundations, preclinical studies using animal models, and clinical trials with human subjects. However, translation from basic animal research to treatment of human conditions is not straightforward. Preclinical studies in animals may not replicate across labs, and a multitude of preclinical leads have failed in human clinical trials. Inspired by recent generative models for semi-supervised action recognition and probabilistic 3D human motion prediction, we are developing a system that learns animal behavior from unstructured video frames without labels or annotations. Our approach extends a generative model to incorporate adversarial inference, and transformer-based self-attention modules.
Topic: AI for Quantum Physics & Appearance Modeling
Department:
Computer Science
Faculty Mentor:
Corey Toler-Franklin, ct3219@columbia.edu
Ph.D. Student Mentor(s):
TBD
Terms Available:
Fall, Spring, Summer
Student Level:
Junior, Senior, Graduate
Prerequisites:
Python and/or C/C++, Machine Learning experience (a plus but not required)
Credit:
0-3 credits independent study
Stipend:
TBD
Application Requirements:
Application Deadline:
Open until filled.
Website:
Project Description:
Quantum Level Optical Interactions in Complex Materials
The wavelength dependence of fluorescence is used in the physical sciences for material analysis and identification. However, fluorescent measurement techniques like mass spectrometry are expensive and often destructive. Empirical measurement systems effectively simulate material appearance but are time consuming, requiring densely sampled measurements. Leveraging GPU processing and shared super computing resources, we develop deep learning models that incorporate principles from quantum mechanics theory to solve large scale many-body problems in physics for non-invasive identification of complex proteinaceous materials.
The wavelength dependence of fluorescence is used in the physical sciences for material analysis and identification. However, fluorescent measurement techniques like mass spectrometry are expensive and often destructive. Empirical measurement systems effectively simulate material appearance but are time consuming, requiring densely sampled measurements. Leveraging GPU processing and shared super computing resources, we develop deep learning models that incorporate principles from quantum mechanics theory to solve large scale many-body problems in physics for non-invasive identification of complex proteinaceous materials.
Topic: AI for Multimodal Data & Document Analysis
Department:
Computer Science
Faculty Mentor:
Corey Toler-Franklin, ct3219@columbia.edu
Ph.D. Student Mentor(s):
TBD
Terms Available:
Fall, Spring, Summer
Student Level:
Junior, Senior, Graduate
Prerequisites:
Python and/or C/C++, Machine Learning experience (a plus but not required)
Credit:
0-3 credits independent study
Stipend:
TBD
Application Requirements:
Application Deadline:
Open until filled.
Website:
Project Description:
Deciphering Findings from the Tulsa Race Massacre Death Investigation
The Tulsa Race Massacre (1921) destroyed a flourishing Black community and left up to 300 people dead. More than 1000 homes were burned and destroyed. Efforts are underway to locate the bodies of victims and reconstruct lost historical information for their families. Collaborating with the Tulsa forensics team, we are developing spectral imaging methods (on-site) for deciphering information on eroded materials (stone engravings, rusted metal, and deteriorated wood markings), and a novel multimodal transformer network to associate recovered information on gravestones with death certificates and geographical information from public records.
The Tulsa Race Massacre (1921) destroyed a flourishing Black community and left up to 300 people dead. More than 1000 homes were burned and destroyed. Efforts are underway to locate the bodies of victims and reconstruct lost historical information for their families. Collaborating with the Tulsa forensics team, we are developing spectral imaging methods (on-site) for deciphering information on eroded materials (stone engravings, rusted metal, and deteriorated wood markings), and a novel multimodal transformer network to associate recovered information on gravestones with death certificates and geographical information from public records.
