Integration of Deep Learning and Neuroscience整合神经科学和深度学习


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) the 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.

假设:1 大脑也优化损失函数 2 损失函数在大脑不同区域和时期都不同 3 优化操作是在针对行为计算问题的预定结构上实现的

In support of these hypotheses, we argue that a range of implementations of credit assignment through multiple layers of neurons are compatible with our current knowledge of neural circuitry, and that the brain’s specialized systems can be interpreted as enabling efficient optimization for specific problem classes.


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.


1. Introduction

Putative differences between conventional and brain-like neural network designs. (A) In conventional deep learning, supervised training is based on externally-supplied, labeled data. (B) In the brain, supervised training of networks can still occur via ...

1.1. Hypothesis 1 – the brain optimizes cost functions

1.2. Hypothesis 2 – cost functions are diverse across areas and change over development

1.3. Hypothesis 3 – specialized systems allow efficient solution of key computational problems

2. The brain can optimize cost functions

2.1. Local self-organization and optimization without multi-layer credit assignment

2.2. Biological implementation of optimization

2.2.1. The need for efficient gradient descent in multi-layer networks

2.2.2. Biologically plausible approximations of gradient descent Temporal credit assignment: Spiking networks

2.3. Other principles for biological learning

2.3.1. Exploiting biological neural mechanisms

2.3.2. Learning in the cortical sheet

2.3.3. One-shot learning

Human learning is often one-shot

2.3.4. Active learning

Human learning is often active and deliberate

2.4. Differing biological requirements for supervised and reinforcement learning

3. The cost functions are diverse across brain areas and time

3.1. How cost functions may be represented and applied

3.2. Cost functions for unsupervised learning

3.2.1. Matching the statistics of the input data using generative models

3.2.2. Cost functions that approximate properties(概念属性) of the world


3.3. Cost functions for supervised learning

3.4. Repurposing reinforcement learning for diverse internal cost functions

3.4.1. Cost functions for bootstrapping learning in the human environment

3.4.2. Cost functions for learning by imitation and through social feedback

3.4.3. Cost functions for story generation and understanding

4. Optimization occurs in the context of specialized structures

4.1. Structured forms of memory

4.1.1. Content addressable memories

4.1.2. Working memory buffers

4.1.3. Storing state in association with saliency

4.2. Structured routing systems

4.2.1. Attention

4.2.2. Buffers

4.2.3. Discrete gating of information flow between buffers

4.3. Structured state representations to enable efficient algorithms

4.3.1. Continuous predictive control

4.3.2. Hierarchical control

Importantly, many of the control problems we appear to be solving are hierarchical.

4.3.3. Spatial planning

Spatial planning requires solving shortest-path problems subject to constraints.

4.3.4. Variable binding

Language and reasoning appear to present a problem for neural networks (Minsky, 1991; Marcus, 2001; Hadley, 2009):


4.3.5. Hierarchical syntax

Fixed, static hierarchies (e.g., the hierarchical organization of cortical areas Felleman and Van Essen, 1991) only take us so far:

4.3.6. Mental programs and imagination

Humans excel at stitching together sub-actions to form larger actions (Verwey, 1996; Acuna et al., 2014; Sejnowski and Poizner, 2014). Structured, serial, hierarchical probabilistic programs

4.4. Other specialized structures

4.5. Relationships with other cognitive frameworks involving specialized systems

5. Machine learning inspired neuroscience

5.1. Hypothesis 1– existence of cost functions

5.2. Hypothesis 2– biological fine-structure of cost functions

5.3. Hypothesis 3– embedding within a pre-structured architecture

6. Neuroscience inspired machine learning

6.1. Hypothesis 1– existence of cost functions

6.2. Hypothesis 2– biological fine-structure of cost functions

6.3. Hypothesis 3– embedding within a pre-structured architecture

7. Did evolution separate cost functions from optimization algorithms?

8. Conclusions

原文 请阅读原文


原文发布于微信公众号 - CreateAMind(createamind)





0 条评论
登录 后参与评论




【导读】专知内容组整理了最近人工智能领域相关期刊的5篇最新综述文章,为大家进行介绍,欢迎查看! 1. The Unreasonable Effectivenes...


自识别标记(self-identifying marker) -(2) 用于相机标定的CALTag介绍

CALTag介绍 CALibration Tag(简记为CALTag)是一种平面自识别标记,专门用于自动化相机标定。这种方法有如下几个必杀技完爆传统的标定方法:...



【导读】专知内容组整理了最近五篇知识图谱(Knowledge Graph)相关文章,为大家进行介绍,欢迎查看! 1. DeepPath: A Reinforce...



在下游分析前,最好是先对peak calling 后的ChIP-Seq数据进行质量评估。


【ICCV 2017论文集】计算机视觉顶级会议ICCV2017 Open Access Repository

在这里先整理一些主题系列论文: ICCV 2017- 3D Vision Oral论文如下: Globally-Optimal Inlier Set Maxi...



Basis(基础): MSE(Mean Square Error均方误差),LMS(LeastMean Square最小均方),LSM(Least Square...



目录 什么是ORB 如何解决旋转不变性 如何解决对噪声敏感的问题 关于尺度不变性 关于计算速度 关于性能 Related posts 什么是ORB ? ORB是...


谷歌开源 tf-seq2seq,你也能用谷歌翻译的框架训练模型

【新智元导读】谷歌今天宣布开源 tf-seq2seq,这是一个用于 Tensorflow 的通用编码器-解码器框架,可用于机器翻译、文本总结、会话建模、图说生成...



【导读】专知内容组既前两天推出十六篇推荐系统相关论文之后,今天为大家又推出十篇推荐系统(Recommendation System)相关论文,欢迎查看!



Basis(基础): MSE(Mean Square Error 均方误差), LMS(LeastMean Square 最小均方), LSM(L...