Rxivist logo

Rxivist combines preprints from bioRxiv with data from Twitter to help you find the papers being discussed in your field. Currently indexing 62,736 bioRxiv papers from 278,376 authors.

Towards an integration of deep learning and neuroscience

By Adam H Marblestone, Greg Wayne, Konrad P Kording

Posted 13 Jun 2016
bioRxiv DOI: 10.1101/058545 (published DOI: 10.3389/fncom.2016.00094)

Neuroscience has focused on the detailed implementation of computation, studying neural codes, dynamics and circuits. In machine learning, however, artificial neural networks tend to eschew precisely designed codes, dynamics or circuits in favor of brute force optimization of a cost function, often using simple and relatively uniform initial architectures. Two recent developments have emerged within machine learning that create an opportunity to connect these seemingly divergent perspectives. First, structured architectures are used, including dedicated systems for attention, recursion and various forms of short- and long-term memory storage. Second, cost functions and training procedures have become more complex and are varied across layers and over time. Here we think about the brain in terms of these ideas. We hypothesize that (1) the brain optimizes cost functions, (2) these cost functions are diverse and differ across brain locations and over development, and (3) optimization operates within a pre-structured architecture matched to the computational problems posed by behavior. Such a heterogeneously optimized system, enabled by a series of interacting cost functions, serves to make learning data-efficient and precisely targeted to the needs of the organism. We suggest directions by which neuroscience could seek to refine and test these hypotheses.

Download data

  • Downloaded 26,946 times
  • Download rankings, all-time:
    • Site-wide: 18 out of 62,736
    • In neuroscience: 5 out of 11,207
  • Year to date:
    • Site-wide: 406 out of 62,736
  • Since beginning of last month:
    • Site-wide: 1,613 out of 62,736

Altmetric data


Downloads over time

Distribution of downloads per paper, site-wide


Sign up for the Rxivist weekly newsletter! (Click here for more details.)


News