Computational Principles of Supervised Learning in the Cerebellum - PubMed Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Review
. 2018 Jul 8:41:233-253.
doi: 10.1146/annurev-neuro-080317-061948.

Computational Principles of Supervised Learning in the Cerebellum

Jennifer L Raymond  1 , Javier F Medina  2
Affiliations
Review

Computational Principles of Supervised Learning in the Cerebellum

Jennifer L Raymond et al. Annu Rev Neurosci. .

Abstract

Supervised learning plays a key role in the operation of many biological and artificial neural networks. Analysis of the computations underlying supervised learning is facilitated by the relatively simple and uniform architecture of the cerebellum, a brain area that supports numerous motor, sensory, and cognitive functions. We highlight recent discoveries indicating that the cerebellum implements supervised learning using the following organizational principles: ( a) extensive preprocessing of input representations (i.e., feature engineering), ( b) massively recurrent circuit architecture, ( c) linear input-output computations, ( d) sophisticated instructive signals that can be regulated and are predictive, ( e) adaptive mechanisms of plasticity with multiple timescales, and ( f) task-specific hardware specializations. The principles emerging from studies of the cerebellum have striking parallels with those in other brain areas and in artificial neural networks, as well as some notable differences, which can inform future research on supervised learning and inspire next-generation machine-based algorithms.

Keywords: Purkinje cell; climbing fiber; consolidation; decorrelation; machine learning; plasticity.

PubMed Disclaimer

Figures

Figure 1
Figure 1
Core architecture of supervised learning networks. The essential computational frameworks for implementing supervised learning are shown for (a) an artificial neural network and (b) the cerebellar network. A preprocessing stage (cyan) transforms the input signals to create representations that are a suitable substrate for supervised learning. Those representations are then sent to an adaptive processor (green) that generates responses. Errors are computed by comparing the actual response of the network with the desired response (orange) and are used as instructive signals to adjust the internal parameters (e.g., synaptic weights) of the adaptive processor until it learns to generate the desired response.
Figure 2
Figure 2
Circuit diagram illustrating how supervised learning is implemented in the cerebellar network. The numbers 2–7 correspond to the computational principles described in Sections 2–7 of the main text and indicate the location(s) where each principle is implemented in the cerebellar network. Feedforward paths (black lines) and feedback paths (red lines) are indicated. Each mossy fiber pattern represents an information stream of a specific modality. An example of a multimodal granule cell (filled with four patterns) and a unimodal granule cell (filled with a one-dot pattern) are shown. Abbreviations: CN, cerebellar nucleus; GrC, granule cell; GoC, Golgi cell; IO, inferior olive; MLI, molecular layer interneuron; PkC, Purkinje cell.
Figure 3
Figure 3
Network configurations for supervised learning applications. Depending on the way the adaptive processor is embedded in the broader network, supervised learning can be used for (a) system identification, where the adaptive processor learns to generate a response that mimics that of an unknown system; (b) inverse system identification, where the adaptive processor learns to generate a response that mimics the original input signal before it was transformed or corrupted by an unknown system; (c) noise cancellation, where the adaptive processor learns to generate a response that is a clean version of a signal that was embedded in unwanted noise (in this application, the error signal converges to the signal itself, rather than converging to zero); and (d) prediction, where the adaptive processor takes past values of the input signal to learn to generate a response that predicts what the future values of the input signal will be. These different network configurations have been leveraged extensively in engineering applications. The cerebellum could be embedded in larger brain networks in similar configurations to help support a variety of sensory, motor, and cognitive functions, including supervised learning of inverse models for generating suitable motor commands, as well as supervised learning of forward models for predicting the sensory consequences of our actions and for cancelling out neural noise generated by self-motion.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

See all "Cited by" articles

References

    1. Albus JS. 1971. A theory of cerebellar function. Math. Biosci 10:25–61
    1. Alpaydin E 2014. Introduction to Machine Learning Cambridge, MA: MIT Press
    1. Alvina K, Walter JT, Kohn A, Ellis-Davies G, Khodakhah K. 2008. Questioning the role of rebound firing in the cerebellum. Nat. Neurosci 11:1256–58 - PMC - PubMed
    1. Ankri L, Husson Z, Pietrajtis K, Proville R, Lena C, et al. 2015. A novel inhibitory nucleo-cortical circuit controls cerebellar Golgi cell activity. eLife 4:e06262 - PMC - PubMed
    1. Apps R 2000. Gating of climbing fibre input to cerebellar cortical zones. Prog. Brain Res 124:201–11 - PubMed

Publication types

LinkOut - more resources