COIN: Combinational Intelligent Networks

• Main Author: Miranda, I. D. S.
• Publication Date: 2023
• Other Authors: Arora, A., Susskind, Z., Souza, J. S. A., Jadhao, M. P., Villon, L. A. Q., Dutra, D. L. C., Lima, P. M. V., França, F. M. G., Breternitz Jr., M., John, L. K.
• Language: eng
• Source: Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
• Download full: http://hdl.handle.net/10071/29488
• topic: Weightless neural networks; LogicWiSARD; Binary neural networks; FPGA; ASIC

We introduce Combinational Intelligent Networks (COIN), a machine learning technique that targets edge inference using low-resourced FPGAs or ASICs. COIN is an improvement on LogicWiSARD, a recent weightless neural network that achieves low power, small area, and high throughput. We convert the LogicWiSARD model into a binary neural network, train it using backpropagation, and then convert it to a COIN model. As a result, COIN can achieve higher accuracy than LogicWiSARD or it can require significantly fewer hardware resources when comparing models with similar accuracies. In comparison to a BNN implementation, FINN, small and large COIN models are more energy efficient demonstrating up to 11.5x higher inferences/Joule at similar accuracy. Our tool executes the complete flow, from training to RTL. and is publicly available.