scholarly journals The Gradient Clusteron: A model neuron that learns via dendritic nonlinearities, structural plasticity, and gradient descent

2020 ◽  
Author(s):  
Toviah Moldwin ◽  
Menachem Kalmenson ◽  
Idan Segev
Keyword(s):  
Gradient Descent ◽  
Learning Algorithm ◽  
Initial Conditions ◽  
Model Neuron ◽  
Learning Rule ◽  
Structural Plasticity ◽  
Dependent Manner ◽  
Location Update ◽  
Xor Problem ◽  
Under Performing

Synaptic clustering on neuronal dendrites has been hypothesized to play an important role in implementing pattern recognition. Neighboring synapses on a dendritic branch can interact in a synergistic, cooperative manner via the nonlinear voltage-dependence of NMDA receptors. Inspired by the NMDA receptor, the single-branch clusteron learning algorithm (Mel 1991) takes advantage of location-dependent multiplicative nonlinearities to solve classification tasks by randomly shuffling the locations of “under-performing” synapses on a model dendrite during learning (“structural plasticity”), eventually resulting in synapses with correlated activity being placed next to each other on the dendrite. We propose an alternative model, the gradient clusteron, or G-clusteron, which uses an analytically-derived gradient descent rule where synapses are “attracted to” or “repelled from” each other in an input- and location- dependent manner. We demonstrate the classification ability of this algorithm by testing it on the MNIST handwritten digit dataset and show that, when using a softmax activation function, the accuracy of the G-clusteron on the All-vs-All MNIST task (85.9%) approaches that of logistic regression (92.6%). In addition to the synaptic location update plasticity rule, we also derive a learning rule for the synaptic weights of the G-clusteron (“functional plasticity”) and show that the G-clusteron with both plasticity rules can achieve 89.5% accuracy on the MNIST task and can learn to solve the XOR problem from arbitrary initial conditions.

scholarly journals The gradient clusteron: A model neuron that learns to solve classification tasks via dendritic nonlinearities, structural plasticity, and gradient descent

2021 ◽  
Vol 17 (5) ◽  
pp. e1009015
Author(s):  
Toviah Moldwin ◽  
Menachem Kalmenson ◽  
Idan Segev
Keyword(s):  
Gradient Descent ◽  
Learning Algorithm ◽  
Initial Conditions ◽  
Model Neuron ◽  
Learning Rule ◽  
Structural Plasticity ◽  
Dependent Manner ◽  
Location Update ◽  
Xor Problem ◽  
Classification Tasks

Synaptic clustering on neuronal dendrites has been hypothesized to play an important role in implementing pattern recognition. Neighboring synapses on a dendritic branch can interact in a synergistic, cooperative manner via nonlinear voltage-dependent mechanisms, such as NMDA receptors. Inspired by the NMDA receptor, the single-branch clusteron learning algorithm takes advantage of location-dependent multiplicative nonlinearities to solve classification tasks by randomly shuffling the locations of “under-performing” synapses on a model dendrite during learning (“structural plasticity”), eventually resulting in synapses with correlated activity being placed next to each other on the dendrite. We propose an alternative model, the gradient clusteron, or G-clusteron, which uses an analytically-derived gradient descent rule where synapses are "attracted to" or "repelled from" each other in an input- and location-dependent manner. We demonstrate the classification ability of this algorithm by testing it on the MNIST handwritten digit dataset and show that, when using a softmax activation function, the accuracy of the G-clusteron on the all-versus-all MNIST task (~85%) approaches that of logistic regression (~93%). In addition to the location update rule, we also derive a learning rule for the synaptic weights of the G-clusteron (“functional plasticity”) and show that a G-clusteron that utilizes the weight update rule can achieve ~89% accuracy on the MNIST task. We also show that a G-clusteron with both the weight and location update rules can learn to solve the XOR problem from arbitrary initial conditions.

scholarly journals Aircraft Maintenance Check Scheduling Using Reinforcement Learning

Aerospace ◽  
2021 ◽  
Vol 8 (4) ◽  
pp. 113
Author(s):  
Pedro Andrade ◽  
Catarina Silva ◽  
Bernardete Ribeiro ◽  
Bruno F. Santos
Keyword(s):  
Reinforcement Learning ◽  
Time Horizon ◽  
Learning Algorithm ◽  
Initial Conditions ◽  
Q Learning ◽  
Scheduling Policy ◽  
Real Scenario ◽  
Maintenance Plan ◽  
Small Disturbances

This paper presents a Reinforcement Learning (RL) approach to optimize the long-term scheduling of maintenance for an aircraft fleet. The problem considers fleet status, maintenance capacity, and other maintenance constraints to schedule hangar checks for a specified time horizon. The checks are scheduled within an interval, and the goal is to, schedule them as close as possible to their due date. In doing so, the number of checks is reduced, and the fleet availability increases. A Deep Q-learning algorithm is used to optimize the scheduling policy. The model is validated in a real scenario using maintenance data from 45 aircraft. The maintenance plan that is generated with our approach is compared with a previous study, which presented a Dynamic Programming (DP) based approach and airline estimations for the same period. The results show a reduction in the number of checks scheduled, which indicates the potential of RL in solving this problem. The adaptability of RL is also tested by introducing small disturbances in the initial conditions. After training the model with these simulated scenarios, the results show the robustness of the RL approach and its ability to generate efficient maintenance plans in only a few seconds.

scholarly journals Optimising Performance for NB-IoT UE Devices through Data Driven Models

2021 ◽  
Vol 10 (1) ◽  
pp. 21
Author(s):  
Omar Nassef ◽  
Toktam Mahmoodi ◽  
Foivos Michelinakis ◽  
Kashif Mahmood ◽  
Ahmed Elmokashfi
Keyword(s):  
Neural Network ◽  
Reinforcement Learning ◽  
Gradient Descent ◽  
Deep Neural Network ◽  
Narrow Band ◽  
Learning Algorithm ◽  
Base Station ◽  
User Equipment ◽  
Data Driven ◽  
Superior Performance

This paper presents a data driven framework for performance optimisation of Narrow-Band IoT user equipment. The proposed framework is an edge micro-service that suggests one-time configurations to user equipment communicating with a base station. Suggested configurations are delivered from a Configuration Advocate, to improve energy consumption, delay, throughput or a combination of those metrics, depending on the user-end device and the application. Reinforcement learning utilising gradient descent and genetic algorithm is adopted synchronously with machine and deep learning algorithms to predict the environmental states and suggest an optimal configuration. The results highlight the adaptability of the Deep Neural Network in the prediction of intermediary environmental states, additionally the results present superior performance of the genetic reinforcement learning algorithm regarding its performance optimisation.

scholarly journals Unsupervised learning by competing hidden units

2019 ◽  
Vol 116 (16) ◽  
pp. 7723-7731 ◽  
Author(s):  
Dmitry Krotov ◽  
John J. Hopfield
Keyword(s):  
Learning Algorithm ◽  
Lower Layer ◽  
Learning Rule ◽  
Backpropagation Algorithm ◽  
Feedforward Networks ◽  
Feature Detectors ◽  
End To End ◽  
Hidden Layer ◽  
Full Network ◽  
Global Inhibition

It is widely believed that end-to-end training with the backpropagation algorithm is essential for learning good feature detectors in early layers of artificial neural networks, so that these detectors are useful for the task performed by the higher layers of that neural network. At the same time, the traditional form of backpropagation is biologically implausible. In the present paper we propose an unusual learning rule, which has a degree of biological plausibility and which is motivated by Hebb’s idea that change of the synapse strength should be local—i.e., should depend only on the activities of the pre- and postsynaptic neurons. We design a learning algorithm that utilizes global inhibition in the hidden layer and is capable of learning early feature detectors in a completely unsupervised way. These learned lower-layer feature detectors can be used to train higher-layer weights in a usual supervised way so that the performance of the full network is comparable to the performance of standard feedforward networks trained end-to-end with a backpropagation algorithm on simple tasks.

A novel methodology to explore the periodic gait of a biped walker under uncertainty using a machine learning algorithm

Robotica ◽  
2021 ◽  
pp. 1-16
Author(s):  
Namjung Kim ◽  
Bongwon Jeong ◽  
Kiwon Park
Keyword(s):  
Limit Cycle ◽  
Systematic Approach ◽  
Learning Algorithm ◽  
Initial Conditions ◽  
Angular Displacement ◽  
External Disturbance ◽  
Rehabilitation Robotics ◽  
Stable Region ◽  
Gait Rehabilitation ◽  
External Disturbances

Abstract In this paper, we present a systematic approach to improve the understanding of stability and robustness of stability against the external disturbances of a passive biped walker. First, a multi-objective, multi-modal particle swarm optimization (MOMM-PSO) algorithm was employed to suggest the appropriate initial conditions for a given biped walker model to be stable. The MOMM-PSO with ring topology and special crowding distance (SCD) used in this study can find multiple local minima under multiple objective functions by limiting each agent’s search area properly without determining a large number of parameters. Second, the robustness of stability under external disturbances was studied, considering an impact in the angular displacement sampled from the probabilistic distribution. The proposed systematic approach based on MOMM-PSO can find multiple initial conditions that lead the biped walker in the periodic gait, which could not be found by heuristic approaches in previous literature. In addition, the results from the proposed study showed that the robustness of stability might change depending on the location on a limit cycle where immediate angular displacement perturbation occurs. The observations of this study imply that the symmetry of the stable region about the limit cycle will break depending on the accelerating direction of inertia. We believe that the systematic approach developed in this study significantly increased the efficiency of finding the appropriate initial conditions of a given biped walker and the understanding of robustness of stability under the unexpected external disturbance. Furthermore, a novel methodology proposed for biped walkers in the present study may expand our understanding of human locomotion, which in turn may suggest clinical strategies for gait rehabilitation and help develop gait rehabilitation robotics.

Internal Calibration System Using Learning Algorithm With Gradient Descent

2020 ◽  
Vol 17 (9) ◽  
pp. 1503-1507
Author(s):  
Chan-Yong Jung ◽  
Kyung-Bin Bae ◽  
Dong-Chan Kim ◽  
Seong-Ook Park
Keyword(s):  
Gradient Descent ◽  
Learning Algorithm ◽  
Calibration System ◽  
Internal Calibration

The Road to Chaos by Time-Asymmetric Hebbian Learning in Recurrent Neural Networks

2007 ◽  
Vol 19 (1) ◽  
pp. 80-110 ◽  
Author(s):  
Colin Molter ◽  
Utku Salihoglu ◽  
Hugues Bersini
Keyword(s):  
Supervised Learning ◽  
Hebbian Learning ◽  
Learning Algorithm ◽  
Initial Conditions ◽  
A Priori ◽  
Computational Cost ◽  
Chaotic Regime ◽  
Dynamical Regime ◽  
New Form ◽  
The Impact

This letter aims at studying the impact of iterative Hebbian learning algorithms on the recurrent neural network's underlying dynamics. First, an iterative supervised learning algorithm is discussed. An essential improvement of this algorithm consists of indexing the attractor information items by means of external stimuli rather than by using only initial conditions, as Hopfield originally proposed. Modifying the stimuli mainly results in a change of the entire internal dynamics, leading to an enlargement of the set of attractors and potential memory bags. The impact of the learning on the network's dynamics is the following: the more information to be stored as limit cycle attractors of the neural network, the more chaos prevails as the background dynamical regime of the network. In fact, the background chaos spreads widely and adopts a very unstructured shape similar to white noise. Next, we introduce a new form of supervised learning that is more plausible from a biological point of view: the network has to learn to react to an external stimulus by cycling through a sequence that is no longer specified a priori. Based on its spontaneous dynamics, the network decides “on its own” the dynamical patterns to be associated with the stimuli. Compared with classical supervised learning, huge enhancements in storing capacity and computational cost have been observed. Moreover, this new form of supervised learning, by being more “respectful” of the network intrinsic dynamics, maintains much more structure in the obtained chaos. It is still possible to observe the traces of the learned attractors in the chaotic regime. This complex but still very informative regime is referred to as “frustrated chaos.”

Sign in / Sign up

Export Citation Format

Share Document