 |
ML Newsnew | past | best | rss | submit | about |
| NengoDL: Combining deep learning and neuromorphic modelling methods (arxiv.org) | |
| 2 points by Seanny123 on May 31, 2018 | hide | past | pdf | discuss on HN | |
|
In plain words: NengoDL is a toolkit for building brain-like neural models, mixing them with deep learning parts like image-recognizing networks, and running them in one place. It also trains those models using deep learning's optimization tricks, and benchmarks show it simulates them efficiently on standard hardware. AbstractNengoDL is a software framework designed to combine the strengths of neuromorphic modelling and deep learning. NengoDL allows users to construct biologically detailed neural models, intermix those models with deep learning elements (such as convolutional networks), and then efficiently simulate those models in an easy-to-use, unified framework. In addition, NengoDL allows users to apply deep learning training methods to optimize the parameters of biological neural models. In this paper we present basic usage examples, benchmarking, and details on the key implementation elements of NengoDL. More details can be found at https://www.nengo.ai/nengo-dl . | |
| add comment on HN |