2 citations · 6 across the 18 of their papers we have counts for
5 papers · 1 filter
Continual Learning of Recurrent Neural Networks by Locally Aligning Distributed Representations
Alexander Ororbia, Ankur Mali, C. Lee Giles +1
Temporal models based on recurrent neural networks have proven to be quite powerful in a wide variety of applications. However, training these models often relies on back-propagati…
A Neural Temporal Model for Human Motion Prediction
Anand Gopalakrishnan, Ankur Mali, Dan Kifer +2
We propose novel neural temporal models for predicting and synthesizing human motion, achieving state-of-the-art in modeling long-term motion trajectories while being competitive w…
Biologically Motivated Algorithms for Propagating Local Target Representations
Alexander G. Ororbia, Ankur Mali
Finding biologically plausible alternatives to back-propagation of errors is a fundamentally important challenge in artificial neural network research. In this paper, we propose a…
Learned Neural Iterative Decoding for Lossy Image Compression Systems
Alexander G. Ororbia, Ankur Mali, Jian Wu +3
For lossy image compression systems, we develop an algorithm, iterative refinement, to improve the decoder's reconstruction compared to standard decoding techniques. Specifically,…
Conducting Credit Assignment by Aligning Local Representations
Alexander G. Ororbia, Ankur Mali, Daniel Kifer +1
Using back-propagation and its variants to train deep networks is often problematic for new users. Issues such as exploding gradients, vanishing gradients, and high sensitivity to…