paper-with-me

홈 › Papers

Differentiable Weightless Neural Networks

2024-10-14 · Alan T. L. Bacellar, Zachary Susskind, Mauricio Breternitz Jr., Eugene John, Lizy K. John, Priscila M. V. Lima, Felipe M. G. França

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 technique for approximate differentiation of binary values. We propose Learnable Mapping, Learnable Reduction, and Spectral Regularization to further improve the accuracy and efficiency of these models. We evaluate DWNs in three edge computing contexts: (1) an FPGA-based hardware accelerator, where they demonstrate superior latency, throughput, energy efficiency, and model area compared to state-of-the-art solutions, (2) a low-power microcontroller, where they achieve preferable accuracy to XGBoost while subject to stringent memory constraints, and (3) ultra-low-cost chips, where they consistently outperform small models in both accuracy and projected hardware area. DWNs also compare favorably against leading approaches for tabular datasets, with higher average rank. Overall, our work positions DWNs as a pioneering solution for edge-compatible high-throughput neural networks.

📄 PDF Abstract BibTeX arXiv:2410.11112

Code (1)

alanbacellar/DWN 공식 구현 pytorch

Tasks

Edge-computing

Similar Papers 제목 키워드 기반

Differentiable Weightless Controllers: Learning Logic Circuits for Continuous Control

2025-12-01 · Fabian Kresse, Christoph H. Lampert arxiv

Controlling autonomous systems under real-world conditions often requires policies that can be evaluated with low latency and minimal energy consumption. Unfortunately, these conditions are at odds with the use of high-p…

Continuous Control

Process mining classification with a weightless neural network

2020-09-25 · Rafael Garcia Barbastefano, Maria Clara Lippi, Diego Carvalho

Using a weightless neural network architecture WiSARD we propose a straightforward graph to retina codification to represent business process graph flows avoiding kernels, and we present how WiSARD outperforms the classi…

ClassificationGeneral Classification

Weightless Neural Networks for Continuously Trainable Personalized Recommendation Systems

2025-09-15 · Rafayel Latif, Satwik Behera, Ali Al-Ebrahim arxiv

Given that conventional recommenders, while deeply effective, rely on large distributed systems pre-trained on aggregate user data, incorporating new data necessitates large training cycles, making them slow to adapt to …

Collaborative FilteringRecommendation Systems

Learn Weightlessness: Imitate Non-Self-Stabilizing Motions on Humanoid Robot

2026-04-23 · Yucheng Xin, Jiacheng Bao, Haoran Yang, Wenqiang Que 외 arxiv

The integration of imitation and reinforcement learning has enabled remarkable advances in humanoid whole-body control, facilitating diverse human-like behaviors. However, research on environment-dependent motions remain…

Reinforcement Learning

Memory via Temporal Delays in weightless Spiking Neural Network

2022-02-15 · Hananel Hazan, Simon Caby, Christopher Earl, Hava Siegelmann 외

A common view in the neuroscience community is that memory is encoded in the connection strength between neurons. This perception led artificial neural network models to focus on connection weights as the key variables t…