Desaturating coefficient for projection learning rule

1996 ◽  
pp. 469-476 ◽  
Author(s):  
Dmitry O. Gorodnichy
Keyword(s):  
Learning Rule

ARFIS: Adaptive-Receiver-Based Fuzzy Inference System for Diffusion- Based Molecular Communications

2020 ◽  
Vol 16 (2) ◽  
pp. 280-289
Author(s):  
Ghalib H. Alshammri ◽  
Walid K. M. Ahmed ◽  
Victor B. Lawrence
Keyword(s):  
Fuzzy Inference System ◽  
Fuzzy Inference ◽  
Detection Threshold ◽  
Learning Rule ◽  
Optimal Number ◽  
Molecular Communication ◽  
Inference System ◽  
Detection Scheme ◽  
Adaptive Receiver ◽  
Detection Schemes

Background: The architecture and sequential learning rule-based underlying ARFIS (adaptive-receiver-based fuzzy inference system) are proposed to estimate and predict the adaptive threshold-based detection scheme for diffusion-based molecular communication (DMC). Method: The proposed system forwards an estimate of the received bits based on the current molecular cumulative concentration, which is derived using sequential training-based principle with weight and bias and an input-output mapping based on both human knowledge in the form of fuzzy IFTHEN rules. The ARFIS architecture is employed to model nonlinear molecular communication to predict the received bits over time series. Result: This procedure is suitable for binary On-OFF-Keying (Book signaling), where the receiver bio-nanomachine (Rx Bio-NM) adapts the 1/0-bit detection threshold based on all previous received molecular cumulative concentrations to alleviate the inter-symbol interference (ISI) problem and reception noise. Conclusion: Theoretical and simulation results show the improvement in diffusion-based molecular throughput and the optimal number of molecules in transmission. Furthermore, the performance evaluation in various noisy channel sources shows promising improvement in the un-coded bit error rate (BER) compared with other threshold-based detection schemes in the literature.

scholarly journals Effects of memristive synapse radiation interactions on learning in spiking neural networks

2021 ◽  
Vol 3 (5) ◽  
Author(s):  
Sumedha Gandharava Dahl ◽  
Robert C. Ivans ◽  
Kurtis D. Cantley
Keyword(s):  
Action Potentials ◽  
Radiation Effects ◽  
Synaptic Weight ◽  
Learning Rule ◽  
Spike Timing ◽  
Spiking Neural Network ◽  
Synaptic Action ◽  
Drift Model ◽  
Spatio Temporal ◽  
Post Synaptic Neuron

AbstractThis study uses advanced modeling and simulation to explore the effects of external events such as radiation interactions on the synaptic devices in an electronic spiking neural network. Specifically, the networks are trained using the spike-timing-dependent plasticity (STDP) learning rule to recognize spatio-temporal patterns (STPs) representing 25 and 100-pixel characters. Memristive synapses based on a TiO2 non-linear drift model designed in Verilog-A are utilized, with STDP learning behavior achieved through bi-phasic pre- and post-synaptic action potentials. The models are modified to include experimentally observed state-altering and ionizing radiation effects on the device. It is found that radiation interactions tend to make the connection between afferents stronger by increasing the conductance of synapses overall, subsequently distorting the STDP learning curve. In the absence of consistent STPs, these effects accumulate over time and make the synaptic weight evolutions unstable. With STPs at lower flux intensities, the network can recover and relearn with constant training. However, higher flux can overwhelm the leaky integrate-and-fire post-synaptic neuron circuits and reduce stability of the network.

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.

scholarly journals CONCURRENT MAP BUILDING AND LOCALIZATION ON INDOOR DYNAMIC ENVIRONMENTS

2002 ◽  
Vol 16 (03) ◽  
pp. 361-374 ◽  
Author(s):  
JUAN ANDRADE-CETTO ◽  
ALBERTO SANFELIU
Keyword(s):  
Learning Rule ◽  
Dynamic Environments ◽  
Position Estimation ◽  
Indoor Environments ◽  
Map Building ◽  
Robust Learning ◽  
Map Construction ◽  
Map Updating ◽  
Dynamic Map ◽  
Robot Position

A system that builds and maintains a dynamic map for a mobile robot is presented. A learning rule associated to each observed landmark is used to compute its robustness. The position of the robot during map construction is estimated by combining sensor readings, motion commands, and the current map state by means of an Extended Kalman Filter. The combination of landmark strength validation and Kalman filtering for map updating and robot position estimation allows for robust learning of moderately dynamic indoor environments.

scholarly journals The Role of Weight Normalization in Competitive Learning

1994 ◽  
Vol 6 (2) ◽  
pp. 255-269 ◽  
Author(s):  
Geoffrey J. Goodhill ◽  
Harry G. Barrow
Keyword(s):  
Learning Rule ◽  
Competitive Learning ◽  
Fixed Amount

The effect of different kinds of weight normalization on the outcome of a simple competitive learning rule is analyzed. It is shown that there are important differences in the representation formed depending on whether the constraint is enforced by dividing each weight by the same amount (“divisive enforcement”) or subtracting a fixed amount from each weight (“subtractive enforcement”). For the divisive cases weight vectors spread out over the space so as to evenly represent “typical” inputs, whereas for the subtractive cases the weight vectors tend to the axes of the space, so as to represent “extreme” inputs. The consequences of these differences are examined.

Spike-Timing-Dependent Hebbian Plasticity as Temporal Difference Learning

2001 ◽  
Vol 13 (10) ◽  
pp. 2221-2237 ◽  
Author(s):  
Rajesh P. N. Rao ◽  
Terrence J. Sejnowski
Keyword(s):  
Cortical Neuron ◽  
Action Potentials ◽  
Learning Rule ◽  
Spike Timing ◽  
Biophysical Model ◽  
Excitatory Synapses ◽  
Temporal Difference ◽  
Temporal Difference Learning ◽  
Neocortical Neurons ◽  
Hebbian Plasticity

A spike-timing-dependent Hebbian mechanism governs the plasticity of recurrent excitatory synapses in the neocortex: synapses that are activated a few milliseconds before a postsynaptic spike are potentiated, while those that are activated a few milliseconds after are depressed. We show that such a mechanism can implement a form of temporal difference learning for prediction of input sequences. Using a biophysical model of a cortical neuron, we show that a temporal difference rule used in conjunction with dendritic backpropagating action potentials reproduces the temporally asymmetric window of Hebbian plasticity observed physiologically. Furthermore, the size and shape of the window vary with the distance of the synapse from the soma. Using a simple example, we show how a spike-timing-based temporal difference learning rule can allow a network of neocortical neurons to predict an input a few milliseconds before the input's expected arrival.

Sign in / Sign up

Export Citation Format

Share Document