6 papers
From Arithmetic to Logic: The Resilience of Logic and Lookup-Based Neural Networks Under Parameter Bit-Flips
Alan T. L. Bacellar, Sathvik Chemudupati, Shashank Nag +4
The deployment of deep neural networks (DNNs) in safety-critical edge environments necessitates robustness against hardware-induced bit-flip errors. While empirical studies indicat…
Single-Round Scalable Analytic Federated Learning
Alan T. L. Bacellar, Mustafa Munir, Felipe M. G. França +3
Federated Learning (FL) is plagued by two key challenges: high communication overhead and performance collapse on heterogeneous (non-IID) data. Analytic FL (AFL) provides a single-…
LL-ViT: Edge Deployable Vision Transformers with Look Up Table Neurons
Shashank Nag, Alan T. L. Bacellar, Zachary Susskind +9
Vision Transformers have been tremendously successful in computer vision tasks. However, their large computational, memory, and energy demands are a challenge for edge inference on…
Differentiable Weightless Neural Networks
Alan T. L. Bacellar, Zachary Susskind, Mauricio Breternitz +4
We introduce the Differentiable Weightless Neural Network (DWN), a model based on interconnected lookup tables. Training of DWNs is enabled by a novel Extended Finite Difference te…
nanoML for Human Activity Recognition
Alan T. L. Bacellar, Mugdha P. Jadhao, Shashank Nag +3
Human Activity Recognition (HAR) is critical for applications in healthcare, fitness, and IoT, but deploying accurate models on resource-constrained devices remains challenging due…
Shrinking the Giant : Quasi-Weightless Transformers for Low Energy Inference
Shashank Nag, Alan T. L. Bacellar, Zachary Susskind +9
Transformers are set to become ubiquitous with applications ranging from chatbots and educational assistants to visual recognition and remote sensing. However, their increasing com…