151 citations · 208 across the 22 of their papers we have counts for
8 papers · 1 filter
Signatures of Steerability in Activation Space of Language Models
Prajjwal Bhattarai, Tuka Alhanai
Steering language models using a set of contrastive representations has been a canonical and computationally efficient method for controlling model behavior. Despite this success i…
Knowledge distillation through geometry-aware representational alignment
Prajjwal Bhattarai, Mohammad Amjad, Dmytro Zhylko +1
Knowledge distillation is a common paradigm for transferring capabilities from larger models to smaller ones. While traditional distillation methods leverage a probabilistic diverg…
MoENAS: Mixture-of-Expert based Neural Architecture Search for jointly Accurate, Fair, and Robust Edge Deep Neural Networks
Lotfi Abdelkrim Mecharbat, Alberto Marchisio, Muhammad Shafique +2
There has been a surge in optimizing edge Deep Neural Networks (DNNs) for accuracy and efficiency using traditional optimization techniques such as pruning, and more recently, empl…
Distribution-Free Uncertainty Quantification in Mechanical Ventilation Treatment: A Conformal Deep Q-Learning Framework
Niloufar Eghbali, Tuka Alhanai, Mohammad M. Ghassemi
Mechanical Ventilation (MV) is a critical life-support intervention in intensive care units (ICUs). However, optimal ventilator settings are challenging to determine because of the…
The Broad Impact of Feature Imitation: Neural Enhancements Across Financial, Speech, and Physiological Domains
Reza Khanmohammadi, Tuka Alhanai, Mohammad M. Ghassemi
Initialization of neural network weights plays a pivotal role in determining their performance. Feature Imitating Networks (FINs) offer a novel strategy by initializing weights to…
MambaNet: A Hybrid Neural Network for Predicting the NBA Playoffs
Reza Khanmohammadi, Sari Saba-Sadiya, Sina Esfandiarpour +2
In this paper, we present Mambanet: a hybrid neural network for predicting the outcomes of Basketball games. Contrary to other studies, which focus primarily on season games, this…
Nightly Automobile Claims Prediction from Telematics-Derived Features: A Multilevel Approach
Allen R. Williams, Yoolim Jin, Anthony Duer +2
In recent years it has become possible to collect GPS data from drivers and to incorporate this data into automobile insurance pricing for the driver. This data is continuously col…
Feature Imitating Networks
Sari Saba-Sadiya, Tuka Alhanai, Mohammad M Ghassemi
In this paper, we introduce a novel approach to neural learning: the Feature-Imitating-Network (FIN). A FIN is a neural network with weights that are initialized to reliably approx…