Predictive learning as a network mechanism for extracting low-dimensional latent space representations

Recanatesi, Stefano; Farrell, Matthew; Lajoie, Guillaume; Denève, Sophie; Rigotti, Mattia; Shea‐Brown, Eric

doi:10.1038/s41467-021-21696-1

Cited by 58 publications

(49 citation statements)

References 70 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Both of these models are abstract, as we are not primarily concerned with the architecture of the predictive model, only its overall behavior. We first consider a network that uses inhibitory feedback to cancel the predictable aspects of its input, in line with models of predictive coding ( 67 – 69 ). We then consider a linear–nonlinear mapping that provides a prediction of

from a partially corrupted readout.…”

Section: Resultsmentioning

confidence: 99%

“…Some theories propose that neural populations retain a latent state that is used to predict future inputs ( 67 – 69 ). This prediction is compared to incoming information to generate a prediction error, which is fed back through recurrent interactions to update the latent state.…”

Section: Resultsmentioning

confidence: 99%

“…We found that a readout population can use an internal model to maintain a consistent interpretation of an unstable encoding population. Such internal models are widely hypothesized to exist in various guises ( 64 , 66 , 67 , 69 ). We did not address how these internal models are learned initially, nor how they might be updated.…”

Section: Discussionmentioning

confidence: 99%

See 2 more Smart Citations

Self-healing codes: How stable neural populations can track continually reconfiguring neural representations

Rule

O’Leary

2022

Proc. Natl. Acad. Sci. U.S.A.

View full text Add to dashboard Cite

As an adaptive system, the brain must retain a faithful representation of the world while continuously integrating new information. Recent experiments have measured population activity in cortical and hippocampal circuits over many days and found that patterns of neural activity associated with fixed behavioral variables and percepts change dramatically over time. Such “representational drift” raises the question of how malleable population codes can interact coherently with stable long-term representations that are found in other circuits and with relatively rigid topographic mappings of peripheral sensory and motor signals. We explore how known plasticity mechanisms can allow single neurons to reliably read out an evolving population code without external error feedback. We find that interactions between Hebbian learning and single-cell homeostasis can exploit redundancy in a distributed population code to compensate for gradual changes in tuning. Recurrent feedback of partially stabilized readouts could allow a pool of readout cells to further correct inconsistencies introduced by representational drift. This shows how relatively simple, known mechanisms can stabilize neural tuning in the short term and provides a plausible explanation for how plastic neural codes remain integrated with consolidated, long-term representations.

show abstract

from a partially corrupted readout.…”

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Self-healing codes: How stable neural populations can track continually reconfiguring neural representations

Rule

O’Leary

2022

Proc. Natl. Acad. Sci. U.S.A.

View full text Add to dashboard Cite

show abstract

“…Soft modes: Trained systems often show 'soft' modes even if training did not explicitly seek such softness (16,17,145,146). Soft modes correspond to normal modes with low energy eigenvalue in equilibrium systems, or more generally, a small Lyapunov exponent.…”

Section: Network Dynamicsmentioning

confidence: 99%

Learning without neurons in physical systems

Stern¹,

Murugan²

2022

Preprint

View full text Add to dashboard Cite

Learning is traditionally studied in biological or computational systems. The power of learning frameworks in solving hard inverse-problems provides an appealing case for the development of 'physical learning' in which physical systems adopt desirable properties on their own without computational design. It was recently realized that large classes of physical systems can physically learn through local learning rules, autonomously adapting their parameters in response to observed examples of use. We review recent work in the emerging field of physical learning, describing theoretical and experimental advances in areas ranging from molecular self-assembly to flow networks and mechanical materials. Physical learning machines provide multiple practical advantages over computer designed ones, in particular by not requiring an accurate model of the system, and their ability to autonomously adapt to changing needs over time. As theoretical constructs, physical learning machines afford a novel perspective on how physical constraints modify abstract learning theory.

show abstract

“…However these methods are usually based on probabilistic models, incorporate latent dynamics, and allow for more nonlinear relationships between the latent factors and activity. See: Paninski and Cunningham [2018], Linderman and Gershman [2017], Whiteway and Butts [2019], Hurwitz et al [2021], Recanatesi et al [2021] Representational Similarity Analyses. While these methods have been popular as a means of comparing ANNs to neural activity, they can also be applied to look for theoretically-motivated encoding schemes or compare across different neural populations within a single system, thereby providing insights into how information is transformed.…”

Section: The Toolboxmentioning

confidence: 99%

Testing the Tools of Systems Neuroscience on Artificial Neural Networks

W.¹

2022

Preprint

View full text Add to dashboard Cite

Neuroscientists apply a range of common analysis tools to recorded neural activity in order to glean insights into how neural circuits implement computations. Despite the fact that these tools shape the progress of the field as a whole, we have little empirical evidence that they are effective at quickly identifying the phenomena of interest. Here I argue that these tools should be explicitly tested and that artificial neural networks (ANNs) are an appropriate testing grounds for them. The recent resurgence of the use of ANNs as models of everything from perception to memory to motor control stems from a rough similarity between artificial and biological neural networks and the ability to train these networks to perform complex high-dimensional tasks. These properties, combined with the ability to perfectly observe and manipulate these systems, makes them well-suited for vetting the tools of systems and cognitive neuroscience. I provide here both a roadmap for performing this testing and a list of tools that are suitable to be tested on ANNs. Using ANNs to reflect on the extent to which these tools provide a productive understanding of neural systems-and on exactly what understanding should mean here-has the potential to expedite progress in the study of the brain.

show abstract

Predictive learning as a network mechanism for extracting low-dimensional latent space representations

Cited by 58 publications

References 70 publications

Self-healing codes: How stable neural populations can track continually reconfiguring neural representations

Self-healing codes: How stable neural populations can track continually reconfiguring neural representations

Learning without neurons in physical systems

Testing the Tools of Systems Neuroscience on Artificial Neural Networks

Contact Info

Product

Resources

About