About Me
Lorem ipsum dolor sit amet consectetur adipisicing elit. Sequi cupiditate cumque reprehenderit voluptas. Harum, cum, hic odio quis magni sapiente saepe delectus nostrum cumque soluta error dicta, quaerat sunt minus!
Lorem, ipsum dolor sit amet consectetur adipisicing elit. Enim itaque nihil omnis corrupti ad sequi quo iure. Accusantium eos sed magnam. Id, rem! Magni nisi sint omnis natus voluptas officia dignissimos voluptatibus unde repudiandae deleniti, explicabo nemo, modi vel cum?
Lorem ipsum dolor sit amet consectetur adipisicing elit. Deserunt veritatis corporis ea delectus illo pariatur, laboriosam suscipit optio perspiciatis! Quaerat, consequuntur odit? Et error, officiis quisquam, aliquid velit sit sapiente cum sed recusandae expedita beatae tempore illo omnis numquam. Saepe explicabo veritatis eos sunt. Maiores nostrum eius perspiciatis quae eligendi?
Education
PhD in Computer Science 2004 - 2008
Prestigious University
Doctoral research focused on machine learning algorithms for pattern recognition and data mining. Developed novel approaches for structured sparsity in high-dimensional data.
- Dissertation: "Structured Sparsity in High-Dimensional Data: Theory and Algorithms"
- Advisor: Dr. John Smith
- Received the Best PhD Thesis Award
Master of Science in Computer Science 2002 - 2004
State University
Advanced studies in machine learning, data mining, and artificial intelligence. Specialized in neural networks and pattern recognition.
- Thesis: "Neural Networks for Pattern Recognition in Medical Images"
- GPA: 3.9/4.0
- Received Academic Excellence Scholarship
Bachelor of Science in Computer Science 1998 - 2002
University of Technology
Comprehensive education in computer science fundamentals, programming, algorithms, and mathematics. Graduated with honors.
- Major: Computer Science
- Minor: Mathematics
- Graduated Summa Cum Laude
News & Updates
New Paper Accepted at ICML 2023
Our paper on "Deep Learning for Survival Prediction in Cancer Patients" has been accepted at the International Conference on Machine Learning.
June 15, 2023
Research Grant Awarded
We have been awarded a $500,000 research grant from the National Science Foundation for our project on "Machine Learning for Drug Discovery".
May 28, 2023
PhD Student Wins Best Paper Award
Congratulations to Jane Smith for winning the Best Paper Award at the International Conference on Medical Image Computing.
April 12, 2023
New Collaboration with Medical School
We are excited to announce a new collaboration with the University Medical School to apply AI techniques for medical image analysis.
March 5, 2023
Invited Talk at AAAI 2023
I will be giving an invited talk on "Deep Graph Learning for Biomedical Applications" at the AAAI Conference on Artificial Intelligence.
February 18, 2023
Workshop on Machine Learning for Healthcare
We are organizing a workshop on "Machine Learning for Healthcare" at the upcoming NeurIPS conference. Submissions are now open.
January 30, 2023
New Research Lab Opening
Our new AI for Healthcare Research Lab is now open. We have state-of-the-art facilities for conducting cutting-edge research.
December 10, 2022
Supervised PhD Students
-
Jane Smith (2023) - "Deep Learning for Medical Image Segmentation"
Current Position
Assistant Professor at Stanford University
-
John Doe (2022) - "Machine Learning for Drug Discovery"
Current Position
Senior Research Scientist at Pfizer
-
Emily Johnson (2021) - "Graph Neural Networks for Social Network Analysis"
Current Position
Data Scientist at Meta
-
Michael Brown (2020) - "Structured Sparsity in High-Dimensional Data"
Current Position
Research Scientist at Google AI
-
Sarah Davis (2019) - "Deep Learning for Survival Prediction"
Current Position
Assistant Professor at MIT
-
Robert Wilson (2018) - "Big Data Analytics for Genomics"
Current Position
Senior Bioinformatician at Broad Institute
-
Jennifer Miller (2017) - "Computer Vision for Facial Behavior Analysis"
Current Position
Senior Research Engineer at Apple
Supervised Master Students
-
David Taylor (2023) - "Machine Learning for Non-intrusive Load Monitoring"
Current Position
Software Engineer at Tesla
-
Lisa Anderson (2023) - "3D Modeling in Medical Images"
Current Position
PhD Student at Carnegie Mellon University
-
James Thomas (2022) - "Deep Learning for Survival Prediction"
Current Position
Data Scientist at Microsoft
-
Mary Jackson (2022) - "Image-Omics Data Analytics"
Current Position
Research Associate at Mayo Clinic
-
Christopher White (2021) - "Structured Sparsity Applications"
Current Position
Machine Learning Engineer at Amazon
-
Patricia Harris (2021) - "Magnetic Resonance Imaging Analysis"
Current Position
PhD Student at University of Toronto
-
Richard Martin (2020) - "Human Behavior Analysis Using AI"
Current Position
AI Researcher at NVIDIA
Information for Future Students
I am always looking for motivated and talented students to join my research group. If you are interested in pursuing a PhD or Master's degree under my supervision, please feel free to contact me.
My research group focuses on developing novel machine learning algorithms for real-world applications, particularly in healthcare and biomedicine. We have collaborations with medical schools, hospitals, and industry partners.
Prospective students should have a strong background in computer science, mathematics, or a related field. Experience with machine learning, deep learning, and programming is highly desirable.
Academic & Work Experience
Academic Experience
Work Experience
Professor of Computer Science 2018 - Present
University of Technology
Leading research in machine learning and AI, teaching graduate and undergraduate courses, and supervising PhD and Master's students.
- Established the AI for Healthcare Research Lab
- Secured over $2M in research funding
- Received the Excellence in Teaching Award (2021)
Associate Professor 2013 - 2018
State University
Conducted research in machine learning, developed new courses in deep learning, and mentored graduate students.
- Published 50+ papers in top-tier conferences and journals
- Developed the first deep learning course at the university
- Received the Early Career Researcher Award (2015)
Assistant Professor 2010 - 2013
Technical Institute
Started academic career, taught introductory computer science courses, and built research program in machine learning.
- Established collaborations with industry partners
- Supervised first PhD student to completion
- Received the Best New Faculty Award (2011)
Postdoctoral Researcher 2008 - 2010
Prestigious Research Institute
Conducted advanced research in machine learning algorithms and their applications to real-world problems.
- Developed novel algorithms for structured sparsity
- Collaborated with leading researchers in the field
- Published in top machine learning conferences
Senior Research Scientist 2006 - 2008
Tech Innovations Inc.
Led machine learning research team, developed AI solutions for various applications, and filed patents.
- Developed machine learning models for predictive analytics
- Led a team of 5 researchers and engineers
- Filed 3 patents related to AI technologies
Research Scientist 2004 - 2006
Data Solutions Corp.
Developed machine learning algorithms for data mining and pattern recognition in large datasets.
- Improved data processing efficiency by 40%
- Developed algorithms adopted by major clients
- Received the Innovation Award (2005)
Machine Learning Engineer 2002 - 2004
AI Systems Ltd.
Implemented machine learning solutions for various industries, including finance and healthcare.
- Developed predictive models for financial forecasting
- Collaborated with healthcare providers on AI solutions
- Contributed to open-source machine learning libraries
Software Developer 2000 - 2002
Software Dynamics
Developed software applications and gained experience in data processing and algorithm implementation.
- Led development of data processing tools
- Implemented optimization algorithms
- Received recognition for innovative solutions
Research Summary
My research focuses on developing novel machine learning and deep learning algorithms for complex real-world problems. I am particularly interested in applications in healthcare, biomedicine, and drug discovery. My work combines theoretical foundations with practical applications, aiming to develop methods that are both mathematically sound and computationally efficient.
Over the years, I have worked on various topics including deep learning, graph neural networks, structured sparsity, medical image analysis, and survival prediction. My research has been published in top-tier conferences and journals, and has been recognized with several awards.
I collaborate with researchers from diverse fields including computer science, medicine, biology, and engineering. These interdisciplinary collaborations have led to novel approaches and solutions to challenging problems.
Research Interests
Deep Graph Learning
- Developing novel graph neural network architectures for complex relational data
- Applications in social network analysis, recommendation systems, and knowledge graphs
- Scalable algorithms for large-scale graph data
- Interpretability and explainability of graph neural networks
Machine Learning for Drug Discovery
- Deep learning models for molecular property prediction
- Virtual screening and drug-target interaction prediction
- Generative models for de novo drug design
- Multi-task learning for drug repurposing
Deep Learning for Survival Prediction
- Novel deep learning models for survival analysis
- Handling censored data in deep learning frameworks
- Applications in cancer prognosis and treatment planning
- Interpretable models for clinical decision support
Big Image-Omics Data Analytics
- Integration of medical imaging and genomics data
- Multi-modal deep learning for precision medicine
- Scalable algorithms for large-scale biomedical data
- Applications in cancer research and personalized treatment
Human/Facial Behavior
- Computer vision for facial expression recognition
- Deep learning models for behavior analysis
- Applications in affective computing and mental health
- Privacy-preserving techniques for behavior analysis
Structured Sparsity: Theory, Algorithms and Applications
- Theoretical foundations of structured sparsity
- Efficient optimization algorithms for structured sparse models
- Applications in feature selection and interpretability
- Integration with deep learning frameworks
Magnetic Resonance Imaging
- Deep learning for MRI reconstruction and enhancement
- Automated segmentation of anatomical structures
- Quantitative analysis of MRI data
- Applications in neuroimaging and musculoskeletal imaging
3D Modeling, Simulation and Segmentation in Medical Images
- Deep learning for 3D medical image segmentation
- Physically-based simulation for surgical planning
- 3D reconstruction from 2D medical images
- Applications in surgical navigation and training
Machine Learning Algorithm Development for Non-intrusive Load Monitoring
- Deep learning models for energy disaggregation
- Real-time monitoring of electrical appliances
- Privacy-preserving techniques for energy data
- Applications in smart grids and energy efficiency
Publications
Deep Learning for Survival Prediction in Cancer Patients
International Conference on Machine Learning (ICML), 2023
We propose a novel deep learning framework for survival prediction in cancer patients. Our model combines convolutional neural networks for feature extraction from medical images with recurrent neural networks for processing longitudinal clinical data. The framework is evaluated on a large-scale dataset of over 10,000 patients with various types of cancer, demonstrating superior performance compared to existing methods.
@inproceedings{smith2023deep,
title={Deep Learning for Survival Prediction in Cancer Patients},
author={Smith, John and Doe, Jane and Johnson, Michael},
booktitle={International Conference on Machine Learning (ICML)},
pages={1234--1243},
year={2023},
organization={PMLR}
}
Graph Neural Networks for Drug-Target Interaction Prediction
Advances in Neural Information Processing Systems (NeurIPS), 2022
This paper presents a novel graph neural network architecture for predicting drug-target interactions. Our approach leverages both the molecular structure of drugs and the sequence information of target proteins to predict binding affinity. Experimental results on benchmark datasets demonstrate that our method outperforms state-of-the-art approaches by a significant margin.
@inproceedings{doe2022graph,
title={Graph Neural Networks for Drug-Target Interaction Prediction},
author={Doe, Jane and Wilson, Robert and Johnson, Emily},
booktitle={Advances in Neural Information Processing Systems (NeurIPS)},
pages={2345--2356},
year={2022}
}
Structured Sparsity in High-Dimensional Data: Theory and Algorithms
Journal of Machine Learning Research (JMLR), 2022
We present a comprehensive theoretical and algorithmic framework for structured sparsity in high-dimensional data. Our work extends traditional sparsity-inducing norms to incorporate structural constraints on the sparsity patterns. We derive theoretical guarantees for recovery and develop efficient optimization algorithms for various structured sparsity models.
@article{johnson2022structured,
title={Structured Sparsity in High-Dimensional Data: Theory and Algorithms},
author={Johnson, Michael and Davis, Sarah and Smith, John},
journal={Journal of Machine Learning Research},
volume={23},
number={1},
pages={3456--3480},
year={2022}
}
Deep Learning for Medical Image Segmentation: A Survey
IEEE Transactions on Medical Imaging, 2022
This paper provides a comprehensive survey of deep learning techniques for medical image segmentation. We review and categorize existing methods based on their architectural design, training strategies, and application domains. We also discuss current challenges and future research directions in this rapidly evolving field.
@article{wilson2022deep,
title={Deep Learning for Medical Image Segmentation: A Survey},
author={Wilson, Robert and Miller, Jennifer and Doe, Jane},
journal={IEEE Transactions on Medical Imaging},
volume={41},
number={3},
pages={789--812},
year={2022},
publisher={IEEE}
}
Multi-modal Deep Learning for Image-Omics Data Integration
Medical Image Computing and Computer Assisted Intervention (MICCAI), 2021
We propose a multi-modal deep learning framework for integrating medical imaging and genomics data. Our approach uses attention mechanisms to effectively combine information from different modalities and learn cross-modal representations. Experimental results on several cancer datasets demonstrate the effectiveness of our method for precision medicine applications.
@inproceedings{davis2021multi,
title={Multi-modal Deep Learning for Image-Omics Data Integration},
author={Davis, Sarah and Taylor, David and Johnson, Michael},
booktitle={Medical Image Computing and Computer Assisted Intervention (MICCAI)},
pages={4567--4578},
year={2021},
organization={Springer}
}
Computer Vision for Facial Behavior Analysis: A Deep Learning Approach
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021
This paper presents a deep learning approach for facial behavior analysis. Our method combines convolutional neural networks for feature extraction with transformer architectures for modeling temporal dynamics. We evaluate our approach on several benchmark datasets for facial expression recognition and action unit detection, achieving state-of-the-art results.
@inproceedings{miller2021computer,
title={Computer Vision for Facial Behavior Analysis: A Deep Learning Approach},
author={Miller, Jennifer and Anderson, Lisa and Wilson, Robert},
booktitle={IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
pages={5678--5689},
year={2021}
}
3D Modeling and Simulation in Medical Images: A Deep Learning Framework
International Conference on Computer Vision (ICCV), 2021
We propose a deep learning framework for 3D modeling and simulation in medical images. Our approach combines 3D convolutional neural networks for segmentation with differentiable rendering techniques for realistic simulation. Experimental results on various medical imaging modalities demonstrate the effectiveness of our method for surgical planning and training.
@inproceedings{taylor20213d,
title={3D Modeling and Simulation in Medical Images: A Deep Learning Framework},
author={Taylor, David and Thomas, James and Davis, Sarah},
booktitle={International Conference on Computer Vision (ICCV)},
pages={6789--6800},
year={2021}
}
Machine Learning for Non-intrusive Load Monitoring: A Review
Applied Energy, 2021
This paper provides a comprehensive review of machine learning techniques for non-intrusive load monitoring (NILM). We categorize existing approaches based on their underlying methodologies and discuss their strengths and limitations. We also identify key challenges and future research directions in the field of NILM.
@article{anderson2021machine,
title={Machine Learning for Non-intrusive Load Monitoring: A Review},
author={Anderson, Lisa and Jackson, Mary and Miller, Jennifer},
journal={Applied Energy},
volume={285},
pages={116439},
year={2021},
publisher={Elsevier}
}
Deep Learning for MRI Reconstruction: A Survey
Magnetic Resonance in Medicine, 2020
This paper provides a comprehensive survey of deep learning techniques for MRI reconstruction. We review and categorize existing methods based on their network architectures, training strategies, and application domains. We also discuss current challenges and future research directions in this rapidly evolving field.
@article{thomas2020deep,
title={Deep Learning for MRI Reconstruction: A Survey},
author={Thomas, James and White, Christopher and Taylor, David},
journal={Magnetic Resonance in Medicine},
volume={84},
number={4},
pages={2238--2257},
year={2020},
publisher={Wiley Online Library}
}
Graph Neural Networks for Social Network Analysis
The Web Conference (WWW), 2020
We propose a novel graph neural network architecture for social network analysis. Our approach leverages both the structural information of the network and the content features of nodes to learn effective representations. Experimental results on several social network datasets demonstrate the effectiveness of our method for various tasks including community detection and link prediction.
@inproceedings{jackson2020graph,
title={Graph Neural Networks for Social Network Analysis},
author={Jackson, Mary and Martin, Richard and Thomas, James},
booktitle={The Web Conference (WWW)},
pages={789--802},
year={2020}
}
Deep Learning for Survival Prediction: A Comprehensive Review
Artificial Intelligence in Medicine, 2020
This paper provides a comprehensive review of deep learning techniques for survival prediction. We categorize existing approaches based on their underlying methodologies and discuss their strengths and limitations. We also identify key challenges and future research directions in the field of survival analysis.
@article{smith2020deep,
title={Deep Learning for Survival Prediction: A Comprehensive Review},
author={Smith, John and Johnson, Emily and Brown, Michael},
journal={Artificial Intelligence in Medicine},
volume={107},
pages={101875},
year={2020},
publisher={Elsevier}
}
Drug Discovery with Deep Learning: A Survey
Briefings in Bioinformatics, 2020
This paper provides a comprehensive survey of deep learning techniques for drug discovery. We review and categorize existing methods based on their applications in various stages of the drug discovery pipeline. We also discuss current challenges and future research directions in this rapidly evolving field.
@article{doe2020drug,
title={Drug Discovery with Deep Learning: A Survey},
author={Doe, Jane and Davis, Sarah and Wilson, Robert},
journal={Briefings in Bioinformatics},
volume={21},
number={5},
pages={1601--1615},
year={2020},
publisher={Oxford University Press}
}
Structured Sparsity Methods for High-Dimensional Data Analysis
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019
We present a comprehensive framework for structured sparsity in high-dimensional data analysis. Our approach extends traditional sparsity-inducing norms to incorporate structural constraints on the sparsity patterns. We derive theoretical guarantees for recovery and develop efficient optimization algorithms for various structured sparsity models.
@article{johnson2019structured,
title={Structured Sparsity Methods for High-Dimensional Data Analysis},
author={Johnson, Michael and Miller, Jennifer and Taylor, David},
journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
volume={41},
number={12},
pages={2988--3003},
year={2019},
publisher={IEEE}
}
Deep Learning for Medical Image Analysis: A Survey
Neurocomputing, 2019
This paper provides a comprehensive survey of deep learning techniques for medical image analysis. We review and categorize existing methods based on their architectural design, training strategies, and application domains. We also discuss current challenges and future research directions in this rapidly evolving field.
@article{wilson2019deep,
title={Deep Learning for Medical Image Analysis: A Survey},
author={Wilson, Robert and Anderson, Lisa and Thomas, James},
journal={Neurocomputing},
volume={335},
pages={11--26},
year={2019},
publisher={Elsevier}
}
Facial Behavior Analysis with Deep Learning: A Review
ACM Computing Surveys, 2019
This paper provides a comprehensive review of deep learning techniques for facial behavior analysis. We categorize existing approaches based on their underlying methodologies and discuss their strengths and limitations. We also identify key challenges and future research directions in the field of facial behavior analysis.
@article{davis2019facial,
title={Facial Behavior Analysis with Deep Learning: A Review},
author={Davis, Sarah and Jackson, Mary and White, Christopher},
journal={ACM Computing Surveys},
volume={52},
number={2},
pages={1--38},
year={2019},
publisher={ACM New York, NY, USA}
}
Downloads
Deep Survival
A deep learning framework for survival analysis with support for various types of censoring and competing risks.
GraphDTI
Graph neural network models for drug-target interaction prediction with molecular graph representations.
SparsityNet
Efficient algorithms for structured sparsity in high-dimensional data with applications to feature selection.
Med3DSeg
3D medical image segmentation using deep learning with state-of-the-art performance on multiple datasets.
ImageOmics
Multi-modal deep learning framework for integrating medical imaging and genomics data for precision medicine.
FaceBehavior
Deep learning models for facial behavior analysis with applications in affective computing and mental health.
Med3D
3D modeling, simulation, and segmentation in medical images with applications in surgical planning and training.
NILM-ML
Machine learning algorithms for non-intrusive load monitoring with real-time performance and high accuracy.
Teaching
-
Machine Learning
CS 540Fall 2023, Spring 2023, Fall 2022, Spring 2022This course provides a broad introduction to machine learning and statistical pattern recognition. Topics include supervised learning (generative/discriminative learning, parametric/non-parametric learning, neural networks, support vector machines), unsupervised learning (clustering, dimensionality reduction, recommender systems), and learning theory (bias/variance tradeoffs, practical advice). -
Deep Learning
CS 640Fall 2023, Fall 2022, Fall 2021This course covers the fundamentals of deep learning with a focus on applications. Topics include neural network architectures, convolutional neural networks, recurrent neural networks, transformers, generative models, and deep reinforcement learning. Students will implement and train deep neural networks for a variety of applications. -
Medical Image Analysis
CS 545Spring 2023, Spring 2022, Spring 2021This course introduces the fundamental techniques for medical image analysis. Topics include image preprocessing, segmentation, registration, visualization, and machine learning for medical images. Students will work with real medical imaging data and implement algorithms for various applications. -
Graph Machine Learning
CS 740Fall 2022, Fall 2021This advanced course covers machine learning on graph-structured data. Topics include graph representation learning, graph neural networks, graph transformers, and applications in various domains. Students will read and discuss recent research papers and implement state-of-the-art algorithms. -
Advanced Topics in Machine Learning
CS 840Spring 2022, Spring 2021This seminar course covers advanced topics in machine learning, with a focus on recent research developments. Topics vary each year but may include deep learning theory, reinforcement learning, generative models, and applications in healthcare. Students will read and present research papers and complete a research project. -
Introduction to Data Science
CS 340Fall 2021, Fall 2020This course provides an introduction to the field of data science. Topics include data collection and cleaning, exploratory data analysis, statistical inference, predictive modeling, and data visualization. Students will work with real-world datasets and use various tools and techniques for data analysis.
Contact Information
Address
Department of Computer Science
University of Technology
123 University Avenue
City, State 12345
professor@university.edu
Phone
+1 (123) 456-7890
Office Hours
Monday: 10:00 AM - 12:00 PM
Wednesday: 2:00 PM - 4:00 PM
Friday: 10:00 AM - 12:00 PM