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 co...
"Extreme edge"1 devices, such as smart sensors, are a uniquely challenging environment for the deployment of machine learning. The tiny energy budgets of these devices lie beyond what is feasible for conventional deep neural networks, particularly in high-throughput scenarios, requiring us to rethink how we approach edge inference. In this work, we propose ULEEN, a model and FPGA-based accelerator architecture ...
p. 163-169; Submitted by Santiago Fabio (fabio.ssantiago@hotmail.com) on 2012-10-16T17:36:39Z No. of bitstreams: 1 Leite, KRB, França.pdf: 5262387 bytes, checksum: e5b40901e3df7588a6cdba326ff588ae (MD5); Made available in DSpace on 2012-10-16T17:36:39Z (GMT). No. of bitstreams: 1 Leite, KRB, França.pdf: 5262387 bytes, checksum: e5b40901e3df7588a6cdba326ff588ae (MD5) Previous issue date: 2012; Temporary lakes ar...
p. 05-08; Submitted by JURANDI DE SOUZA SILVA (jssufba@hotmail.com) on 2011-10-19T14:01:52Z No. of bitstreams: 1 a03v13s2.pdf: 35576 bytes, checksum: dfbfff9e3fb6583b6f7200f6cb821179 (MD5); Made available in DSpace on 2011-10-19T14:01:52Z (GMT). No. of bitstreams: 1 a03v13s2.pdf: 35576 bytes, checksum: dfbfff9e3fb6583b6f7200f6cb821179 (MD5) Previous issue date: 2003; Espécies nativas ou endêmicas do semi-árido ...