Biography
Siddharth N. (Sid) is a Reader (Associate Professor) in Explainable AI in the School of Informatics at the University of Edinburgh. Prior to this, he was a Senior Researcher in Engineering at the University of Oxford and a Postdoctoral Scholar in Psychology at Stanford.
He obtained his PhD from Purdue University in Electrical and Computer Engineering. His research broadly involves the confluence of machine learning, computer vision, natural-language processing, cognitive science, robotics, and elements of cognitive neuroscience, leading towards a central research goal to better understand perception and cognition with a view to enabling human-intelligible machine intelligence.
Most Recent Publications
Relating by Contrasting: A Data-efficient Framework for Multimodal Generative Models
Relating by Contrasting: A Data-efficient Framework for Multimodal Generative Models
Capturing Label Characteristics in VAEs
Capturing Label Characteristics in VAEs
Simulation-Based Inference for Global Health Decisions
Simulation-Based Inference for Global Health Decisions
DGPose: Deep Generative Models for Human Body Analysis
DGPose: Deep Generative Models for Human Body Analysis
A Revised Generative Evaluation of Visual Dialogue
A Revised Generative Evaluation of Visual Dialogue
Research Interests
- Explainable AI
- Human-Like Learning
- Unsupervised Representation Learning
- Approximate Probabilistic Inference
- Probabilistic Programming
Research Groups
Related Academics
Most Recent Publications
Relating by Contrasting: A Data-efficient Framework for Multimodal Generative Models
Relating by Contrasting: A Data-efficient Framework for Multimodal Generative Models
Capturing Label Characteristics in VAEs
Capturing Label Characteristics in VAEs
Simulation-Based Inference for Global Health Decisions
Simulation-Based Inference for Global Health Decisions
DGPose: Deep Generative Models for Human Body Analysis
DGPose: Deep Generative Models for Human Body Analysis
A Revised Generative Evaluation of Visual Dialogue
A Revised Generative Evaluation of Visual Dialogue
Publications
Most Recent Publications
Relating by Contrasting: A Data-efficient Framework for Multimodal Generative Models
Relating by Contrasting: A Data-efficient Framework for Multimodal Generative Models
Capturing Label Characteristics in VAEs
Capturing Label Characteristics in VAEs
Simulation-Based Inference for Global Health Decisions
Simulation-Based Inference for Global Health Decisions
DGPose: Deep Generative Models for Human Body Analysis
DGPose: Deep Generative Models for Human Body Analysis
A Revised Generative Evaluation of Visual Dialogue
A Revised Generative Evaluation of Visual Dialogue
DPhil Opportunities
I take on 1-2 PhD students each year. Projects will broadly be on learning/using structured representations of perceptual data, and developing cutting-edge probabilistic inference tools to facilitate this.
Most Recent Publications
Relating by Contrasting: A Data-efficient Framework for Multimodal Generative Models
Relating by Contrasting: A Data-efficient Framework for Multimodal Generative Models
Capturing Label Characteristics in VAEs
Capturing Label Characteristics in VAEs
Simulation-Based Inference for Global Health Decisions
Simulation-Based Inference for Global Health Decisions
DGPose: Deep Generative Models for Human Body Analysis
DGPose: Deep Generative Models for Human Body Analysis
A Revised Generative Evaluation of Visual Dialogue
A Revised Generative Evaluation of Visual Dialogue
