https://www.sciencedirect.com/science/article/pii/S2666389921000647

JavaScript is disabled on your browser. Please enable JavaScript to
use all the features on this page. [1677970858] Skip to main content
Skip to article
Elsevier logo

  * Journals & Books

  * 
  *  Search

RegisterSign in

  * View PDF
  * Download full issue

[                    ]
Patterns

Patterns

Volume 2, Issue 5, 14 May 2021, 100244
Journal home page for Patterns

Review
The overfitted brain: Dreams evolved to assist generalization

Author links open overlay panelErik Hoel ^1
Show more
Share
Cite
https://doi.org/10.1016/j.patter.2021.100244Get rights and content
Under a Creative Commons license
open access

The bigger picture

Dreaming remains a mystery to neuroscience. While various hypotheses
of why brains evolved nightly dreaming have been put forward, many of
these are contradicted by the sparse, hallucinatory, and narrative
nature of dreams, a nature that seems to lack any particular
function. Recently, research on artificial neural networks has shown
that during learning, such networks face a ubiquitous problem: that
of overfitting to a particular dataset, which leads to failures in
generalization and therefore performance on novel datasets. Notably,
the techniques that researchers employ to rescue overfitted
artificial neural networks generally involve sampling from an
out-of-distribution or randomized dataset. The overfitted brain
hypothesis is that the brains of organisms similarly face the
challenge of fitting too well to their daily distribution of stimuli,
causing overfitting and poor generalization. By hallucinating
out-of-distribution sensory stimulation every night, the brain is
able to rescue the generalizability of its perceptual and cognitive
abilities and increase task performance.

Summary

Understanding of the evolved biological function of sleep has
advanced considerably in the past decade. However, no equivalent
understanding of dreams has emerged. Contemporary neuroscientific
theories often view dreams as epiphenomena, and many of the proposals
for their biological function are contradicted by the phenomenology
of dreams themselves. Now, the recent advent of deep neural networks
(DNNs) has finally provided the novel conceptual framework within
which to understand the evolved function of dreams. Notably, all DNNs
face the issue of overfitting as they learn, which is when
performance on one dataset increases but the network's performance
fails to generalize (often measured by the divergence of performance
on training versus testing datasets). This ubiquitous problem in DNNs
is often solved by modelers via "noise injections" in the form of
noisy or corrupted inputs. The goal of this paper is to argue that
the brain faces a similar challenge of overfitting and that nightly
dreams evolved to combat the brain's overfitting during its daily
learning. That is, dreams are a biological mechanism for increasing
generalizability via the creation of corrupted sensory inputs from
stochastic activity across the hierarchy of neural structures. Sleep
loss, specifically dream loss, leads to an overfitted brain that can
still memorize and learn but fails to generalize appropriately.
Herein this "overfitted brain hypothesis" is explicitly developed and
then compared and contrasted with existing contemporary
neuroscientific theories of dreams. Existing evidence for the
hypothesis is surveyed within both neuroscience and deep learning,
and a set of testable predictions is put forward that can be pursued
both in vivo and in silico.

  * Previous article in issue
  * Next article in issue

Keywords

dreams
deep learning
neuroscience
learning
Recommended articles

Cited by (0)

(c) 2021 The Author(s).

Recommended articles

No articles found.

Article Metrics

View article metrics
Elsevier logo with wordmark

  * About ScienceDirect
  * Remote access
  * Shopping cart
  * Advertise
  * Contact and support
  * Terms and conditions
  * Privacy policy

We use cookies to help provide and enhance our service and tailor
content and ads. By continuing you agree to the use of cookies.

Copyright (c) 2023 Elsevier B.V. or its licensors or contributors. 
ScienceDirect(r) is a registered trademark of Elsevier B.V.

ScienceDirect(r) is a registered trademark of Elsevier B.V.

RELX group home page