scholarly journals Biologically plausible learning in recurrent neural networks reproduces neural dynamics observed during cognitive tasks

2016 ◽  
Author(s):  
Thomas Miconi

AbstractNeural activity during cognitive tasks exhibits complex dynamics that flexibly encode task-relevant variables. Chaotic recurrent networks, which spontaneously generate rich dynamics, have been proposed as a model of cortical computation during cognitive tasks. However, existing methods for training these networks are either biologically implausible, and/or require a continuous, real-time error signal to guide learning. Here we show that a biologically plausible learning rule can train such recurrent networks, guided solely by delayed, phasic rewards at the end of each trial. Networks endowed with this learning rule can successfully learn nontrivial tasks requiring flexible (context-dependent) associations, memory maintenance, nonlinear mixed selectivities, and coordination among multiple outputs. The resulting networks replicate complex dynamics previously observed in animal cortex, such as dynamic encoding of task features and selective integration of sensory inputs. We conclude that recurrent neural networks offer a plausible model of cortical dynamics during both learning and performance of flexible behavior.

eLife ◽  
2017 ◽  
Vol 6 ◽  
Author(s):  
Thomas Miconi

Neural activity during cognitive tasks exhibits complex dynamics that flexibly encode task-relevant variables. Chaotic recurrent networks, which spontaneously generate rich dynamics, have been proposed as a model of cortical computation during cognitive tasks. However, existing methods for training these networks are either biologically implausible, and/or require a continuous, real-time error signal to guide learning. Here we show that a biologically plausible learning rule can train such recurrent networks, guided solely by delayed, phasic rewards at the end of each trial. Networks endowed with this learning rule can successfully learn nontrivial tasks requiring flexible (context-dependent) associations, memory maintenance, nonlinear mixed selectivities, and coordination among multiple outputs. The resulting networks replicate complex dynamics previously observed in animal cortex, such as dynamic encoding of task features and selective integration of sensory inputs. We conclude that recurrent neural networks offer a plausible model of cortical dynamics during both learning and performance of flexible behavior.


2004 ◽  
Vol 213 ◽  
pp. 483-486
Author(s):  
David Brodrick ◽  
Douglas Taylor ◽  
Joachim Diederich

A recurrent neural network was trained to detect the time-frequency domain signature of narrowband radio signals against a background of astronomical noise. The objective was to investigate the use of recurrent networks for signal detection in the Search for Extra-Terrestrial Intelligence, though the problem is closely analogous to the detection of some classes of Radio Frequency Interference in radio astronomy.


2003 ◽  
Vol 15 (8) ◽  
pp. 1897-1929 ◽  
Author(s):  
Barbara Hammer ◽  
Peter Tiňo

Recent experimental studies indicate that recurrent neural networks initialized with “small” weights are inherently biased toward definite memory machines (Tiňno, Čerňanský, & Beňušková, 2002a, 2002b). This article establishes a theoretical counterpart: transition function of recurrent network with small weights and squashing activation function is a contraction. We prove that recurrent networks with contractive transition function can be approximated arbitrarily well on input sequences of unbounded length by a definite memory machine. Conversely, every definite memory machine can be simulated by a recurrent network with contractive transition function. Hence, initialization with small weights induces an architectural bias into learning with recurrent neural networks. This bias might have benefits from the point of view of statistical learning theory: it emphasizes one possible region of the weight space where generalization ability can be formally proved. It is well known that standard recurrent neural networks are not distribution independent learnable in the probably approximately correct (PAC) sense if arbitrary precision and inputs are considered. We prove that recurrent networks with contractive transition function with a fixed contraction parameter fulfill the so-called distribution independent uniform convergence of empirical distances property and hence, unlike general recurrent networks, are distribution independent PAC learnable.


iScience ◽  
2021 ◽  
pp. 103178
Author(s):  
Yichen Henry Liu ◽  
Junda Zhu ◽  
Christos Constantinidis ◽  
Xin Zhou

1992 ◽  
Vol 03 (01) ◽  
pp. 83-101 ◽  
Author(s):  
D. Saad

The Minimal Trajectory (MINT) algorithm for training recurrent neural networks with a stable end point is based on an algorithmic search for the systems’ representations in the neighbourhood of the minimal trajectory connecting the input-output representations. The said representations appear to be the most probable set for solving the global perceptron problem related to the common weight matrix, connecting all representations of successive time steps in a recurrent discrete neural networks. The search for a proper set of system representations is aided by representation modification rules similar to those presented in our former paper,1 aimed to support contributing hidden and non-end-point representations while supressing non-contributing ones. Similar representation modification rules were used in other training methods for feed-forward networks,2–4 based on modification of the internal representations. A feed-forward version of the MINT algorithm will be presented in another paper.5 Once a proper set of system representations is chosen, the weight matrix is then modified accordingly, via the Perceptron Learning Rule (PLR) to obtain the proper input-output relation. Computer simulations carried out for the restricted cases of parity and teacher-net problems show rapid convergence of the algorithm in comparison with other existing algorithms, together with modest memory requirements.


2021 ◽  
Author(s):  
Bojian Yin ◽  
Federico Corradi ◽  
Sander M. Bohté

ABSTRACTInspired by more detailed modeling of biological neurons, Spiking neural networks (SNNs) have been investigated both as more biologically plausible and potentially more powerful models of neural computation, and also with the aim of extracting biological neurons’ energy efficiency; the performance of such networks however has remained lacking compared to classical artificial neural networks (ANNs). Here, we demonstrate how a novel surrogate gradient combined with recurrent networks of tunable and adaptive spiking neurons yields state-of-the-art for SNNs on challenging benchmarks in the time-domain, like speech and gesture recognition. This also exceeds the performance of standard classical recurrent neural networks (RNNs) and approaches that of the best modern ANNs. As these SNNs exhibit sparse spiking, we show that they theoretically are one to three orders of magnitude more computationally efficient compared to RNNs with comparable performance. Together, this positions SNNs as an attractive solution for AI hardware implementations.


Sign in / Sign up

Export Citation Format

Share Document