# Towards an integration of deep learning and neuroscience

arXiv: https://arxiv.org/abs/1606.03813 · HTML: https://mlsanity.com/paper/1606.03813/

## Key facts

- Cited by 78 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jun 2016.

## Built on by (most cited first, 30 of 78)

- [Training Spiking Neural Networks Using Lessons From Deep Learning](https://mlsanity.com/paper/2109.12894/) (2021)
- [Partial success in closing the gap between human and machine vision](https://mlsanity.com/paper/2106.07411/) (2021)
- [Recent advances and clinical applications of deep learning in medical image analysis](https://mlsanity.com/paper/2105.13381/) (2021)
- [The Predictive Forward-Forward Algorithm](https://mlsanity.com/paper/2301.01452/) (2023)
- [Signal Propagation: A Framework for Learning and Inference In a Forward Pass](https://mlsanity.com/paper/2204.01723/) (2022)
- [Towards Explainable Traffic Flow Prediction with Large Language Models](https://mlsanity.com/paper/2404.02937/) (2024)
- [Activation Landscapes as a Topological Summary of Neural Network Performance](https://mlsanity.com/paper/2110.10136/) (2021)
- [Inductive biases, pretraining and fine-tuning jointly account for brain responses to speech](https://mlsanity.com/paper/2103.01032/) (2021)
- [A contrastive rule for meta-learning](https://mlsanity.com/paper/2104.01677/) (2021)
- [Toward Learning Human-aligned Cross-domain Robust Models by Countering Misaligned Features](https://mlsanity.com/paper/2111.03740/) (2021)
- [Visual representations in the human brain are aligned with large language models](https://mlsanity.com/paper/2209.11737/) (2022)
- [Predictive coding feedback results in perceived illusory contours in a recurrent neural network](https://mlsanity.com/paper/2102.01955/) (2021)
- [Learning cortical representations through perturbed and adversarial dreaming](https://mlsanity.com/paper/2109.04261/) (2021)
- [Linear Leaky-Integrate-and-Fire Neuron Model Based Spiking Neural Networks and Its Mapping Relationship to Deep Neural Networks](https://mlsanity.com/paper/2207.04889/) (2022)
- [Synergistic information supports modality integration and flexible learning in neural networks solving multiple tasks](https://mlsanity.com/paper/2210.02996/) (2022)
- [A Rubric for Human-like Agents and NeuroAI](https://mlsanity.com/paper/2212.04401/) (2022)
- [Learning efficient backprojections across cortical hierarchies in real time](https://mlsanity.com/paper/2212.10249/) (2022)
- [Spiking Neural Networks and Bio-Inspired Supervised Deep Learning: A Survey](https://mlsanity.com/paper/2307.16235/) (2023)
- [A Quantum Generative Adversarial Network for distributions](https://mlsanity.com/paper/2110.02742/) (2021)
- [Synaptic Plasticity Models and Bio-Inspired Unsupervised Deep Learning: A Survey](https://mlsanity.com/paper/2307.16236/) (2023)
- [Predictive auxiliary objectives in deep RL mimic learning in the brain](https://mlsanity.com/paper/2310.06089/) (2023)
- [Attention Models for Point Clouds in Deep Learning: A Survey](https://mlsanity.com/paper/2102.10788/) (2021)
- [Deep Recurrent Encoder: A scalable end-to-end network to model brain signals](https://mlsanity.com/paper/2103.02339/) (2021)
- [Activation Learning by Local Competitions](https://mlsanity.com/paper/2209.13400/) (2022)
- [Eight challenges in developing theory of intelligence](https://mlsanity.com/paper/2306.11232/) (2023)
- [A Comprehensive Review of AI Agents: Transforming Possibilities in Technology and Beyond](https://mlsanity.com/paper/2508.11957/) (2025)
- [Learning offline: memory replay in biological and artificial reinforcement learning](https://mlsanity.com/paper/2109.10034/) (2021)
- [Cortico-cerebellar networks as decoupling neural interfaces](https://mlsanity.com/paper/2110.11501/) (2021)
- [Building Human-like Communicative Intelligence: A Grounded Perspective](https://mlsanity.com/paper/2201.02734/) (2022)
- [An Extension to Basis-Hypervectors for Learning from Circular Data in Hyperdimensional Computing](https://mlsanity.com/paper/2205.07920/) (2022)

## Abstract (arXiv)

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.