126 citations · 240 across the 13 of their papers we have counts for
13 papers
Mechanistic Mode Connectivity
Ekdeep Singh Lubana, Eric J. Bigelow, Robert P. Dick +2
We study neural network loss landscapes through the lens of mode connectivity, the observation that minimizers of neural networks retrieved via training on a dataset are connected…
Orchestra: Unsupervised Federated Learning via Globally Consistent Clustering
Ekdeep Singh Lubana, Chi Ian Tang, Fahim Kawsar +2
Federated learning is generally used in tasks where labels are readily available (e.g., next word prediction). Relaxing this constraint requires design of unsupervised learning tec…
Do Smart Glasses Dream of Sentimental Visions? Deep Emotionship Analysis for Eyewear Devices
Yingying Zhao, Yuhu Chang, Yutian Lu +8
Emotion recognition in smart eyewear devices is highly valuable but challenging. One key limitation of previous works is that the expression-related information like facial or eye…
Beyond BatchNorm: Towards a Unified Understanding of Normalization in Deep Learning
Ekdeep Singh Lubana, Robert P. Dick, Hidenori Tanaka
Inspired by BatchNorm, there has been an explosion of normalization layers in deep learning. Recent works have identified a multitude of beneficial properties in BatchNorm to expla…
A Reinforcement-Learning-Based Energy-Efficient Framework for Multi-Task Video Analytics Pipeline
Yingying Zhao, Mingzhi Dong, Yujiang Wang +7
Deep-learning-based video processing has yielded transformative results in recent years. However, the video analytics pipeline is energy-intensive due to high data rates and relian…
MemX: An Attention-Aware Smart Eyewear System for Personalized Moment Auto-capture
Yuhu Chang, Yingying Zhao, Mingzhi Dong +7
This work presents MemX: a biologically-inspired attention-aware eyewear system developed with the goal of pursuing the long-awaited vision of a personalized visual Memex. MemX cap…
HVAQ: A High-Resolution Vision-Based Air Quality Dataset
Zuohui Chen, Tony Zhang, Zhuangzhi Chen +3
Air pollutants, such as particulate matter, negatively impact human health. Most existing pollution monitoring techniques use stationary sensors, which are typically sparsely deplo…
How do Quadratic Regularizers Prevent Catastrophic Forgetting: The Role of Interpolation
Ekdeep Singh Lubana, Puja Trivedi, Danai Koutra +1
Catastrophic forgetting undermines the effectiveness of deep neural networks (DNNs) in scenarios such as continual learning and lifelong learning. While several methods have been p…
OrthoReg: Robust Network Pruning Using Orthonormality Regularization
Ekdeep Singh Lubana, Puja Trivedi, Conrad Hougen +2
Network pruning in Convolutional Neural Networks (CNNs) has been extensively investigated in recent years. To determine the impact of pruning a group of filters on a network's accu…
A Gradient Flow Framework For Analyzing Network Pruning
Ekdeep Singh Lubana, Robert P. Dick
Recent network pruning methods focus on pruning models early-on in training. To estimate the impact of removing a parameter, these methods use importance measures that were origina…
The Mason Test: A Defense Against Sybil Attacks in Wireless Networks Without Trusted Authorities
Yue Liu, David R. Bild, Robert P. Dick +2
Wireless networks are vulnerable to Sybil attacks, in which a malicious node poses as many identities in order to gain disproportionate influence. Many defenses based on spatial va…
Performance Analysis of Location Profile Routing
David R. Bild, Yue Liu, Robert P. Dick +2
We propose using the predictability of human motion to eliminate the overhead of distributed location services in human-carried MANETs, dubbing the technique location profile routi…
Aggregate Characterization of User Behavior in Twitter and Analysis of the Retweet Graph
David R. Bild, Yue Liu, Robert P. Dick +2
Most previous analysis of Twitter user behavior is focused on individual information cascades and the social followers graph. We instead study aggregate user behavior and the retwe…