Does computational neuroscience need new synaptic learning paradigms?

Brea, Johanni; Gerstner, Wulfram

doi:10.1016/j.cobeha.2016.05.012

Cited by 38 publications

(37 citation statements)

References 108 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We found that if one combines local rules for synaptic plasticity with learning signals from a separate network that is optimized for inducing fast learning of RSNNs, one-shot learning becomes feasible in a biologically realistic manner. This solves a well-known open problem in computational neuroscience (Brea and Gerstner, 2016). We have also shown that RSNNs can learn in this way to estimate posterior probabilities, thereby providing a new basis for modeling probabilistic computing and learning in RSNNs.…”

Section: Discussionmentioning

confidence: 65%

“…Application 1: One-shot learning of new arm movements Brea and Gerstner (2016) argue that one-shot learning is one of two really important learning capabilities of the brain that are not yet satisfactorily explained by current models in computational neuroscience. We demonstrate that natural e-prop supports one-shot learning in two very different contexts.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

One-shot learning with spiking neural networks

Scherr

Stöckl

Maass

2020

Preprint

View full text Add to dashboard Cite

Understanding how one-shot learning can be accomplished through synaptic plasticity in neural networks of the brain is a major open problem. We propose that approximations to BPTT in recurrent networks of spiking neurons (RSNNs) such as e-prop cannot achieve this because their local synaptic plasticity is gated by learning signals that are rather ad hoc from a biological perspective: Random projections of instantaneously arising losses at the network outputs, analogously as in Broadcast Alignment for feedforward networks. In contrast, synaptic plasticity is gated in the brain by learning signals such as dopamine, which are emitted by specialized brain areas, e.g. VTA. These brain areas have arguably been optimized by evolution to gate synaptic plasticity in such a way that fast learning of survivalrelevant tasks is enabled. We found that a corresponding model architecture, where learning signals are emitted by a separate RSNN that is optimized to facilitate fast learning, enables one-shot learning via local synaptic plasticity in RSNNs for large families of learning tasks. The same learning approach also supports fast spike-based learning of posterior probabilities of potential input sources, thereby providing a new basis for probabilistic reasoning in RSNNs. Our new learning approach also solves an open problem in neuromorphic engineering, where onchip one-shot learning capability is highly desirable for spike-based neuromorphic devices, but could so far not be achieved. Our method can easily be mapped into neuromorphic hardware, and thereby solves this problem.Preprint. Under review.

show abstract

Section: Discussionmentioning

confidence: 65%

Section: Introductionmentioning

confidence: 99%

One-shot learning with spiking neural networks

Scherr

Stöckl

Maass

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…We argue that the above mechanisms of local selforganization are likely insufficient to account for the brain's powerful learning performance (Brea and Gerstner, 2016). To elaborate on the need for an efficient means of gradient computation in the brain, we will first place backpropagation into it's computational context (Hinton, 1989;Baldi and Sadowski, 2015).…”

Section: Biological Implementation Of Optimizationmentioning

confidence: 99%

Towards an integration of deep learning and neuroscience

Marblestone

Wayne

Körding

2016

Preprint

View full text Add to dashboard Cite

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.

show abstract

“…Efforts are underway to effectively train spiking neural networks (Gerstner et al, 2014;Gerstner and Kistler, 2002;O'Connor and Welling, 2016;Huh and Sejnowski, 2017) and endow them with the same cognitive capabilities as their rate-based cousins Zambrano and Bohte, 2016;Kheradpisheh et al, 2016;Lee et al, 2016;Thalmeier et al, 2015). In the same vein, researchers are exploring how probabilistic computations can be performed in neural networks (Pouget et al, 2013;Nessler et al, 2013;Orhan and Ma, 2016;Heeger, 2017) and deriving new biologically plausible synaptic plasticity rules (Schiess et al, 2016;Brea and Gerstner, 2016). Biologically-inspired principles may also be incorporated at a more conceptual level.…”

Section: Next-generation Artificial Neural Networkmentioning

confidence: 99%

Computational Foundations of Natural Intelligence

Gerven

2017

Preprint

View full text Add to dashboard Cite

New developments in AI and neuroscience are revitalizing the quest to understanding natural intelligence, offering insight about how to equip machines with human-like capabilities. This paper reviews some of the computational principles relevant for understanding natural intelligence and, ultimately, achieving strong AI. After reviewing basic principles, a variety of computational modeling approaches is discussed. Subsequently, I concentrate on the use of artificial neural networks as a framework for modeling cognitive processes. This paper ends by outlining some of the challenges that remain to fulfill the promise of machines that show human-like intelligence.

show abstract

Does computational neuroscience need new synaptic learning paradigms?

Cited by 38 publications

References 108 publications

One-shot learning with spiking neural networks

One-shot learning with spiking neural networks

Towards an integration of deep learning and neuroscience

Computational Foundations of Natural Intelligence

Contact Info

Product

Resources

About