# A brain basis of dynamical intelligence for AI and computational neuroscience

arXiv: https://arxiv.org/abs/2105.07284 · HTML: https://mlsanity.com/paper/2105.07284/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 180 references that are in the map.
- First posted on arXiv 15 May 2021.

## Builds on (most cited first, 30 of 31)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [Exploration by Random Network Distillation](https://mlsanity.com/paper/1810.12894/) (2018)
- [Deep Double Descent: Where Bigger Models and More Data Hurt](https://mlsanity.com/paper/1912.02292/) (2019)
- [It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners](https://mlsanity.com/paper/2009.07118/) (2020)
- [Pruning neural networks without any data by iteratively conserving synaptic flow](https://mlsanity.com/paper/2006.05467/) (2020)
- [Agent57: Outperforming the Atari Human Benchmark](https://mlsanity.com/paper/2003.13350/) (2020)
- [Training Deep Spiking Neural Networks using Backpropagation](https://mlsanity.com/paper/1608.08782/) (2016)
- [The Computational Limits of Deep Learning](https://mlsanity.com/paper/2007.05558/) (2020)
- [The Hardware Lottery](https://mlsanity.com/paper/2009.06489/) (2020)
- [Assessing the Scalability of Biologically-Motivated Deep Learning Algorithms and Architectures](https://mlsanity.com/paper/1807.04587/) (2018)
- [Towards deep learning with segregated dendrites](https://mlsanity.com/paper/1610.00161/) (2016)
- [The Unreasonable Effectiveness of Deep Learning in Artificial Intelligence](https://mlsanity.com/paper/2002.04806/) (2020)
- [Linking connectivity, dynamics and computations in low-rank recurrent neural networks](https://mlsanity.com/paper/1711.09672/) (2017)
- [Deep Neural Networks Rival the Representation of Primate IT Cortex for Core Visual Object Recognition](https://mlsanity.com/paper/1406.3284/) (2014)
- [Dense Associative Memory is Robust to Adversarial Inputs](https://mlsanity.com/paper/1701.00939/) (2017)
- [How Can We Be So Dense? The Benefits of Using Highly Sparse Representations](https://mlsanity.com/paper/1903.11257/) (2019)
- [Deep learning tools for the measurement of animal behavior in neuroscience](https://mlsanity.com/paper/1909.13868/) (2019)
- [Brain-Inspired Learning on Neuromorphic Substrates](https://mlsanity.com/paper/2010.11931/) (2020)
- [Equivalence of Equilibrium Propagation and Recurrent Backpropagation](https://mlsanity.com/paper/1711.08416/) (2017)
- [BS4NN: Binarized Spiking Neural Networks with Temporal Coding and Learning](https://mlsanity.com/paper/2007.04039/) (2020)
- [BP-STDP: Approximating Backpropagation using Spike Timing Dependent Plasticity](https://mlsanity.com/paper/1711.04214/) (2017)
- [Generative models as parsimonious descriptions of sensorimotor loops](https://mlsanity.com/paper/1904.12937/) (2019)
- [Activation Relaxation: A Local Dynamical Approximation to Backpropagation in the Brain](https://mlsanity.com/paper/2009.05359/) (2020)
- [Deep Learning for Cognitive Neuroscience](https://mlsanity.com/paper/1903.01458/) (2019)
- [What is the dynamical regime of cerebral cortex?](https://mlsanity.com/paper/1908.10101/) (2019)
- [On the role of theory and modeling in neuroscience](https://mlsanity.com/paper/2003.13825/) (2020)
- [Exploring Exploration: Comparing Children with RL Agents in Unified Environments](https://mlsanity.com/paper/2005.02880/) (2020)
- [Untangling cross-frequency coupling in neuroscience](https://mlsanity.com/paper/1405.7965/) (2014)

## Built on by (most cited first, 1 of 1)

- [Bayesian optimization of distributed neurodynamical controller models for spatial navigation](https://mlsanity.com/paper/2111.00599/) (2021)

## Abstract (arXiv)

The deep neural nets of modern artificial intelligence (AI) have not achieved defining features of biological intelligence, including abstraction, causal learning, and energy-efficiency. While scaling to larger models has delivered performance improvements for current applications, more brain-like capacities may demand new theories, models, and methods for designing artificial learning systems. Here, we argue that this opportunity to reassess insights from the brain should stimulate cooperation between AI research and theory-driven computational neuroscience (CN). To motivate a brain basis of neural computation, we present a dynamical view of intelligence from which we elaborate concepts of sparsity in network structure, temporal dynamics, and interactive learning. In particular, we suggest that temporal dynamics, as expressed through neural synchrony, nested oscillations, and flexible sequences, provide a rich computational layer for reading and updating hierarchical models distributed in long-term memory networks. Moreover, embracing agent-centered paradigms in AI and CN will accelerate our understanding of the complex dynamics and behaviors that build useful world models. A convergence of AI/CN theories and objectives will reveal dynamical principles of intelligence for brains and engineered learning systems. This article was inspired by our symposium on dynamical neuroscience and machine learning at the 6th Annual US/NIH BRAIN Initiative Investigators Meeting.