One-shot learning

One-shot learning is a crucial mechanism for survival and adaptation, enabling rapid acquisition of knowledge from a single experience [1]. Here, we investigated the synaptic plasticity associated with one-shot learning in vivo, focusing on endocannabinoid-mediated long-term potentiation (eCB-LTP) at cortico-striatal synapses [2]. We recorded neural activity in the cortex and striatum of behaving mice subjected to an uncomfortable stimulus in an arena using Neuropixel probes. This task was designed to induce avoidance behavior after a single encounter of the stimulus, thus modeling one-shot le

Continual learning focuses on systems that incrementally acquire and update their knowledge. It is a pressing problem in machine learning as it is challenging to learn new tasks without forgetting knowledge about old ones, a phenomenon known as catastrophic forgetting [1]. Since biological systems are able to efficiently learn and update their knowledge continually during their lifetime, we are interested in principles inspired by these systems to try to tackle this challenge. One of the ideas in biology that is often overlooked in artificial neural networks is Dale’s principle [2], stating th

A central problem in biological learning is how information about the outcome of a decision or behavior can be used to reliably guide learning across distributed neural circuits while obeying biological constraints. This “credit assignment” problem is commonly solved in artificial neural networks through supervised gradient descent and the backpropagation algorithm. In contrast, biological learning is typically modelled using unsupervised Hebbian learning rules. While these rules only use local information to update synaptic weights, and are sometimes combined with weight constraints to reflec

…of pattern completion and unsupervised learning. Here, we propose that Hebbian plasticity is fundamental for computations in biological neural systems. We introduce a novel spiking neural network (SNN) architecture that is enriched by Hebbian synaptic plasticity. We experimentally

One-shot learning can be achieved by animals and algorithms, but how animals do it is poorly understood as most of the algorithms are not biologically plausible. Experiments studying one-shot learning in rodents have shown that after initial gradual learning of associations between cues and locations, new associations can be learned with just a single exposure to each new cue-location pair. Foster, Morris and Dayan (2000) developed a neuro-symbolic actor-critic and coordinate learning agent that exhibited one-shot learning to displaced single locations in an open field maze using dead reckonin

Transformative advances in deep learning, such as deep reinforcement learning, usually rely on gradient-based learning methods such as backpropagation through time (BPTT) as a core learning algorithm. However, BPTT is not argued to be biologically plausible, since it requires to a propagate gradients backwards in time and across neurons. Here, we propose e-prop, a novel gradient-based learning method with local and online weight update rules for recurrent neural networks, and in particular recurrent spiking neural networks (RSNNs). As a result, e-prop has the potential to provide a substantial