Vithursan Thangarasa
Originally from Toronto, Canada, and currently based in the San Francisco Bay Area, I am deeply passionate about neural network compression, large-scale foundation models, and enhancing the efficiency of training large neural networks, with a keen interest in generative AI.
Twitter Google Scholar LinkedIn Github E-MailAll Posts
ICML AMTL 2019 - Differentiable Hebbian Plasticity for Continual Learning
Note: To learn more about continual learning, check out my blog post: Continual Lifelong Learning with Deep Neural Nets.
Gradient Episodic Memory for Continual Learning
On March 20, 2018, I gave a talk to the Machine Learning Research Group (MLRG) at the University of Guelph on continual learning, also called lifelong learni...
Continual Lifelong Learning with Deep Neural Nets
Continual machine learning aims to design and develop computational sytems and algorithms that learn as humans do. For example, as humans we are usually good...
Learning to Teach Neural Networks
On November 28, 2017, I gave a talk to the Machine Learning Research Group (MLRG) at the University of Guelph on different methods for teaching neural networ...
CVPR 2017 - Learning Features by Watching Objects Move (Paper Review)
A salient feature representation can greatly improve the performance of a Deep Neural Network (DNN). In previous state-of-the-art work for computer vision ta...
DevOps for Deep Learning
On May 29, 2017, I gave a talk to the Machine Learning Research Group (MLRG) at the University of Guelph on adopting DevOps technologies to deep learning wor...