activity
20212025
most citedLL-ViT: Edge Deployable Vision Transformers with Look Up Table Neurons

5 citations · 7 across the 6 of their papers we have counts for

collaborators

6 papers

cs.LG20255 cited

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…

cs.LG2024

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…

cs.LG2024

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…

cs.AR2023

ULEEN: A Novel Architecture for Ultra Low-Energy Edge Neural Networks

Zachary Susskind, Aman Arora, Igor D. S. Miranda +9

The deployment of AI models on low-power, real-time edge devices requires accelerators for which energy, latency, and area are all first-order concerns. There are many approaches t…

cs.AR20222 cited

Weightless Neural Networks for Efficient Edge Inference

Zachary Susskind, Aman Arora, Igor Dantas Dos Santos Miranda +8

Weightless Neural Networks (WNNs) are a class of machine learning model which use table lookups to perform inference. This is in contrast with Deep Neural Networks (DNNs), which us…

cs.AI2021

Neuro-Symbolic AI: An Emerging Class of AI Workloads and their Characterization

Zachary Susskind, Bryce Arden, Lizy K. John +2

Neuro-symbolic artificial intelligence is a novel area of AI research which seeks to combine traditional rules-based AI approaches with modern deep learning techniques. Neuro-symbo…