Brain Cell Differences could be Key to Learning in Humans and AI

The new study found that by tweaking the electrical properties of individual cells in simulations of brain networks, the networks learned faster than simulations with identical cells.

They also found that the networks needed fewer of the tweaked cells to get the same results, and that the method is less energy intensive than models with identical cells.

The authors say that their findings could teach us about why our brains are so good at learning, and might also help us to build better artificially intelligent systems, such as digital assistants that can recognise voices and faces, or self-driving car technology.

First author Nicolas Perez, a PhD student at Imperial College London’s Department of Electrical and Electronic Engineering, said: "The brain needs to be energy efficient while still being able to excel at solving complex tasks. Our work suggests that having a diversity of neurons in both brains and AI systems fulfils both these requirements and could boost learning."

The research is published in Nature Communications.

Why is a neuron like a snowflake?

The brain is made up of billions of cells called neurons, which are connected by vast 'neural networks' that allow us to learn about the world. Neurons are like snowflakes: they look the same from a distance but on further inspection it’s clear that no two are exactly alike.

By contrast, each cell in an artificial neural network - the technology on which AI is based - is identical, with only their connectivity varying. Despite the speed at which AI technology is advancing, their neural networks do not learn as accurately or quickly as the human brain - and the researchers wondered if their lack of cell variability might be a culprit.

They set out to study whether emulating the brain by varying neural network cell properties could boost learning in AI. They found that the variability in the cells improved their learning and reduced energy consumption.

Lead author Dr Dan Goodman, of Imperial's Department of Electrical and Electronic Engineering, said: "Evolution has given us incredible brain functions - most of which we are only just beginning to understand. Our research suggests that we can learn vital lessons from our own biology to make AI work better for us."

Tweaked timing

To carry out the study, the researchers focused on tweaking the "time constant" - that is, how quickly each cell decides what it wants to do based on what the cells connected to it are doing. Some cells will decide very quickly, looking only at what the connected cells have just done. Other cells will be slower to react, basing their decision on what other cells have been doing for a while.

After varying the cells’ time constants, they tasked the network with performing some benchmark machine learning tasks: to classify images of clothing and handwritten digits; to recognise human gestures; and to identify spoken digits and commands.

The results show that by allowing the network to combine slow and fast information, it was better able to solve tasks in more complicated, real-world settings.

When they changed the amount of variability in the simulated networks, they found that the ones that performed best matched the amount of variability seen in the brain, suggesting that the brain may have evolved to have just the right amount of variability for optimal learning.

Nicolas added: "We demonstrated that AI can be brought closer to how our brains work by emulating certain brain properties. However, current AI systems are far from achieving the level of energy efficiency that we find in biological systems.

"Next, we will look at how to reduce the energy consumption of these networks to get AI networks closer to performing as efficiently as the brain."

Perez-Nieves N, Leung VCH, Dragotti PL, Goodman DFM.
Neural heterogeneity promotes robust learning.
Nat Commun. 2021 Oct 4;12(1):5791. doi: 10.1038/s41467-021-26022-3

Most Popular Now

Research Shows AI Technology Improves Pa…

Existing research indicates that the accuracy of a Parkinson's disease diagnosis hovers between 55% and 78% in the first five years of assessment. That's partly because Parkinson's sibling movement disorders...

Who's to Blame When AI Makes a Medi…

Assistive artificial intelligence technologies hold significant promise for transforming health care by aiding physicians in diagnosing, managing, and treating patients. However, the current trend of assistive AI implementation could actually...

First Therapy Chatbot Trial Shows AI can…

Dartmouth researchers conducted the first clinical trial of a therapy chatbot powered by generative AI and found that the software resulted in significant improvements in participants' symptoms, according to results...

DMEA sparks: The Future of Digital Healt…

8 - 10 April 2025, Berlin, Germany. Digitalization is considered one of the key strategies for addressing the shortage of skilled workers - but the digital health sector also needs qualified...

DeepSeek: The "Watson" to Doct…

DeepSeek is an artificial intelligence (AI) platform built on deep learning and natural language processing (NLP) technologies. Its core products include the DeepSeek-R1 and DeepSeek-V3 models. Leveraging an efficient Mixture...

Stepping Hill Hospital Announced as SPAR…

Stepping Hill Hospital, part of Stockport NHS Foundation Trust, has replaced its bedside units with state-of-the art devices running a full range of information, engagement, communications and productivity apps, to...

DMEA 2025: Digital Health Worldwide in B…

8 - 10 April 2025, Berlin, Germany. From the AI Act, to the potential of the European Health Data Space, to the power of patient data in Scandinavia - DMEA 2025...