
	Where results make sense

Topic: Hebbian learning

Related Topics

Learning psychology

Donald Olding Hebb

Hebbian theory

Synaptic plasticity

Memory

Morris water maze

Abstract thinking

Critical thinking

Picture thinking

Lateral thinking

Twins (musical group)

Thinking

Ghost crab

Wellington boot

John Cleese

In the News (Tue 8 Dec 09)

Northern Trust

Marvin Harrison

Peter Chernin

Gary Locke

Match Play

Penelope Cruz

Mickey Rourke

AR Rahman

Danny Boyle

Hugh Jackman

	Hebbian learning
		Hebbian learning is a hypothesis for how neuronal connections are enforced in mammalian brains; it is also a technique for weight selection in artificial neural networks.
		A variation of Hebbian learning that takes into account phenomena such a blocking and many other neural learning phenomena is the mathematical model of Harry Klopf, formerly of the Air Force Office of Scientific Research and presently with Wright Patterson Air Force Base.
		Experiments on Hebbian synapse modification mechanisms at the central nervous system synapses of vertebrates are much more difficult to control than are experiments with the relatively simple peripheral nervous system synapses studied in marine invertebrates.
	www.xasa.com /wiki/en/wikipedia/h/he/hebbian_learning.html (499 words)

	Analog VLSI Circuits for Hebbian Learning in Neural Networks
		The voltage across the active/well junction is held to within the offset of the follower; this typically results in a substantial decrease in leakage current from a normal well that is held at the supply voltage of the well transistor.
		Hebbian learning is achieved by gating charge onto or off the storage node when the pre- and post-synaptic spikes are simultaneous or nonsimultaneous, respectively.
		A Hebbian Synapse for spiking neurons is illustrated.
	www.nasatech.com /Briefs/Aug01/NPO20965.html (479 words)

	Hebbian learning
		Hebbian learning is a hypothesis for how neuronal connections are enforced in mammalian brains; it is also a technique for weight selection in artificial neural networks.
		While this means it can be relatively easily coded into a computer program and used to update the weights for a network, it also prohibits the number of applications of Hebbian learning.
		Experiments on Hebbian synapse modification mechanisms at the central nervous system synapses of vertebrates are much more difficult to control than are experiments with the relatively simple peripheral nervous system synapses studied in marine invertebrates.
	publicliterature.org /en/wikipedia/h/he/hebbian_learning.html (448 words)

	Steve Grossberg's "Birth of a Learn Law"
		Incorrect learned associations near the beginning of the list tend to be learned in the forward direction in time, whereas incorrect associations near the end of the list tend to be learned in the backward direction in time (!).
		In particular, real-time learning laws cannot achieve their maximum power unless they are embedded within architectures which enable learning to remain stable through time, free from catastrophic forgetting, particularly when the amount of data becomes large and can change its statistical properties through time.
		For example, the learning laws for sensory and cognitive processes, as in the ART model (e.g., [6]), are often computationally complementary to the learning laws for spatial and motor processes, as in the VAM model [56].
	cns-web.bu.edu /Profiles/Grossberg/Learning.html (3497 words)

	Hebbian Learning
		Learning was based on the modification of synaptic connections between neurons.
		From a neurophysiological perspective, Hebbian learning can be described as a time-dependent, local, highly interactive mechanism that increases synaptic efficacy as a function of pre- and post-synaptic activity.
		Within connectionism, Hebbian learning is an unsupervised training algorithm in which the synaptic strength (weight) is increased if both the source neuron and target neuron are active at the same time.
	neuron-ai.tuke.sk /NCS/VOL1/P3_html/node14.html (427 words)

	Neuromorphic Learning Circuits
		Hebbian learning is THE form of learning that has actually been observed in real neurons.
		Hebbian learning rules adapt to the average input vector direction weighted with the input length.
		Hebbian learning strengthens the connections between neurons that re active in the same image and weakens or makes inhibitory the connections between neuron pairs where one is active and the other is not.
	www.ifi.uio.no /infneuro/Gamle/H2002/hafliger/learning_algos.html (2152 words)

	Hebbian learning - Wikipedia, the free encyclopedia
		This is learning by epoch (weights updated after all the training examples are presented).
		A variation of Hebbian learning that takes into account phenomena such as blocking and many other neural learning phenomena is the mathematical model of Harry Klopf, formerly of the Air Force Office of Scientific Research and presently with Wright-Patterson Air Force Base.
		Klopf's model is considered a far more accurate model of Hebbian learning because it reproduces so many biological phenomena.
	en.wikipedia.org /wiki/Hebbian_learning (716 words)

	Hebbian Learning Rule (Site not responding. Last check: 2007-10-21)
		Hebbian learning adjusts the network's weights such that its output reflects its familiarity with an input.
		Unfortunately, plain Hebbian learning continually strengthens its weights without bound (unless the input data is properly normalized).
		In forced Hebbian, the output of the component is substituted by a desired response for the purpose of weight update.
	www.nd.com /definitions/hebbian.htm (107 words)

	Hebbian theory - Wikipedia, the free encyclopedia
		It has been suggested that Hebbian learning be merged into this article or section.
		Hebbian theory describes a basic mechanism for synaptic plasticity wherein an increase in synaptic efficacy arises from the presynaptic cell's repeated and persistent stimulation of the postsynaptic cell.
		Hebbian theory has been the primary basis for the conventional view that when analyzed from a holistic level, engrams are neuronal nets or neural networks.
	en.wikipedia.org /wiki/Hebbian_theory (406 words)

	The Hebbian Network: The Distributed Representation of Facts
		Now when we learn something about an instance we are also learning about the type and vice versa, if we learn soemthing about a type we are learning about the instances within that type automatically.
		This form of learning is a mathematical abstraction of the principle of synaptic modulation first articulated by Hebb (1949).
		In this exposition, we described the learning rule in terms of the interactions of individual units.
	www.itee.uq.edu.au /~cogs2010/cmc/chapters/Hebbian (2584 words)

	B553: Contrastive Hebbian Learning
		Settling (attractor) networks trained using Hebbian learning, such as Hopfield networks, can be used to solve both auto-associative and hetero-associative problems, but some problems require a hidden layer to mediate the associations.
		Supervised, hetero-associative learning: we would like the network at equilibrium with input and output units clamped to have the same activations as the network at equilibrium with only the inputs clamped.
		Unsupervised, auto-associative learning: we would like the network at equilibrium with an input pattern clamped to stay at equilibrium when the input pattern is unclamped.
	www.cs.indiana.edu /l/www/classes/b553/chl.html (410 words)

	University of Alberta Dictionary of Cognitive Science: Hebbian Learning Rule
		The Hebbian Learning Rule is a learning rule that specifies how much the weight of the connection between two units should be increased or decreased in proportion to the product of their activation.
		The rule builds on Hebbs's 1949 learning rule which states that the connections between two neurons might be strengthened if the neurons fire simultaneously.
		A more powerful learning rule is the delta rule, which utilizes the discrepancy between the desired and actual output of each output unit to change the weights feeding into it.
	www.bcp.psych.ualberta.ca /~mike/Pearl_Street/Dictionary/contents/H/hebbian_learning_rule.html (156 words)

	Approximating Uncertain Term Logic Using Time-Skewed Hebbian Learning
		The Hebbian Logic Network is a unique neural network architecture, in which the relationship between symbolic logic and neural net learning dynamic is fairly simple and clear.
		The exact nature of the update and learning functions that best model brain activity are not known; and the neural net literature is full of update and learning functions that are tuned for particular practical applications or computational experiments.
		The bulk of this paper is oriented toward defining a class of learning functions that are adequate to induce “emergent logical behavior” in a formal neural network.
	www.goertzel.org /dynapsyc/2003/HebbianLogic03.htm (5670 words)

	A brief history of the Hebbian Learning Rule Canadian Psychology - Find Articles
		Commonsense decrees that brain representations must be learned, at least in the case of representations of the shapes of human artefacts such as the letters of the alphabet, tools, and buildings.
		The part of it dealing with the ontogeny of spinal reflexes may well be nonsense, as Hebb maintained, but Brown (2001, 2002) made the interesting discovery that the thesis includes an analysis of the neural learning mechanism underlying Pavlovian conditioning that foreshadows the one he later presented to explain the learning of visual representations.
		When, some dozen or so years later, Hebb needed to specify the neural learning mechanism responsible for the acquisition of shape representations in the brain, it seems that he consciously or unconsciously returned to the formulation in his thesis.
	www.findarticles.com /p/articles/mi_qa3711/is_200302/ai_n9174385 (817 words)

	10.2 Rate-Based Hebbian Learning
		In order to prepare the ground for a thorough analysis of spike-based learning rules in Section 10.3 we will first review the basic concepts of correlation-based learning in a firing rate formalism.
		Locality means that the change of the synaptic efficacy can only depend on local variables, i.e., on information that is available at the site of the synapse, such as pre- and postsynaptic firing rate, and the actual value of the synaptic efficacy, but not on the activity of other neurons.
		A learning rule with only first-order terms gives rise to so-called non-Hebbian plasticity, because pre- or postsynaptic activity alone induces a change of the synaptic efficacy.
	diwww.epfl.ch /~gerstner/SPNM/node72.html (1626 words)

	Hebbian learning - Definition of Hebbian learning by Webster's Online Dictionary
		Hebbian learning - The most common way to train a neural network; a kind of unsupervised learning; named after canadian neuropsychologist, Donald O.
		The algorithm is based on Hebb's Postulate, which states that where one cell's firing repeatedly contributes to the firing of another cell, the magnitude of this contribution will tend to increase gradually with time.
		g., the inability to learn certain patterns, variations such as Signal Hebbian Learning and Differential Hebbian Learning are still used.
	www.webster-dictionary.org /definition/Hebbian+learning (121 words)

	Learning Webs
		Hebbian learning can be implemented on the web, by changing the strength of links depending on how often they are used
		The most basic one is inspired by Hebbian learning, the strengthening of a link between neurons or concepts when these neurons are activated in close succession.
		The equivalent for the web is the "frequency" rule that reinforces a link from document A to document B each time a user moves from A to B. The complementary rule of "symmetry" will moreover reinforce the inverse link from B to A, albeit with a smaller increment.
	pespmc1.vub.ac.be /LEARNWEB.html (843 words)

	LENS Manual: How To Create Hebbian or Other Non-Backprop Networks (Site not responding. Last check: 2007-10-21)
		Because you can redefine the functions that train or test the network at the level of the tick, example, or batch, there is a lot of freedom to implement algorithms that are quite unlike backpropagation.
		For example, imagine you were writing a simple Hebbian rule in which the change to weight Wij should be equal to e Oi Oj, where e is a small epsilon and the O's are the outputs of the two units.
		A final option, given that most Hebbian learning rules are symmetrical and a pair of links will always keep the same weight if they are initialized the same way, is to just change the network resetting procedure to give the corresponding links the same value at the start and then treat them as separate links.
	tedlab.mit.edu /~dr/Lens/progHebbian.html (483 words)

	Competitive Learning Networks (Site not responding. Last check: 2007-10-21)
		One popular scheme for such adaptation is the competitive learning rule, which allows the units to compete for the exclusive right to respond to a particular input pattern.
		One important feature of this learning rule is that renormalization is incorporated into the updating rule such that the sum of synaptic weigts to any output remains 1.
		One way to avoid this problem of not learning is by having all the weights in the network involved in the training with different degrees of strenght.
	www.gc.ssr.upm.es /inves/neural/ann1/unsupmod/CompetLe/CompetLe.htm (723 words)

	Hebbian learning and memory traces (Site not responding. Last check: 2007-10-21)
		The idea that the connections between neurons are involved in learning and memory is due to the anatomist Santiago Ramón y Cajal, who around 1890 had discovered those connections (synapses) in microscopy studies of brain preparations.
		Hebb postulated a simple mechanism for memory formation and associative learning that has been successfully tested in numerous computational models of neural networks.
		Recently, as part of a team work, I have provided evidence of this learning rule in a biological neural network, the antennal lobe, which is the analogue of the olfactory bulb in vertebrates, the brain area that encodes olfactory information.
	www.andrew.cmu.edu /user/rfgalan/hebb/hebb.htm (237 words)

	Neural Gas plus Competitive Hebbian Learning (Site not responding. Last check: 2007-10-21)
		This method (Martinetz and Schulten, 1991, 1994) is a straight-forward superposition of neural gas and competitive Hebbian learning.
		Figure 5.5: Neural gas with competitive Hebbian learning simulation sequence for a ring-shaped uniform probability distribution.
		Figure: Neural gas with competitive Hebbian learning simulation results after 40000 input signals for three different probability distributions (described in the caption of figure 4.4).
	www.neuroinformatik.ruhr-uni-bochum.de /ini/VDM/research/gsn/JavaPaper/node18.html (303 words)

	Competitive Hebbian Learning (Site not responding. Last check: 2007-10-21)
		The method does not change reference vectors at all (which could be interpreted as having a zero learning rate).
		Figure 5.3: Competitive Hebbian learning simulation sequence for a ring-shaped uniform probability distribution.
		Figure: Competitive Hebbian learning simulation results after 40000 input signals for three different probability distributions (described in the caption of figure 4.4).
	www.neuroinformatik.ruhr-uni-bochum.de /ini/VDM/research/gsn/JavaPaper/node17.html (248 words)

	Ruhr-Uni Bochum - Lehrstuhl Mathematik und Informatik - Hebbian Learning in Networks of Spiking Neurons Using Temporal ...
		Computational tasks in biological systems that require short response times can be implemented in a straightforward way by networks of spiking neurons that encode analogue values in temporal coding.
		In particular, we provide learning rules of the Hebbian type in terms of single spiking events of the pre- and postsynaptic neuron and show that the weights approach some value given by the difference between pre- and postsynaptic firing times with arbitrary high precision.
		Our learning rules give rise to a straightforward possibility for realizing very fast pattern analysis tasks with spiking neurons.
	www.ruhr-uni-bochum.de /lmi/mschmitt/hebbianspiking-abs.html (159 words)

	A Comparison of Hebbian Learning Methods for Image Compression using the Mixture of Principal Components Network
		A Comparison of Hebbian Learning Methods for Image Compression using the Mixture of Principal Components Network
		A number of novel adaptive image compression methods have been developed using a new approach to data representation, a mixture of principal components (MPC).
		While Hebbian learning has been effectively used to extract principal components for the MPC, its stability is still a concern in practice.
	www.uoguelph.ca /~rdony/ei98/neural.html (235 words)

	The Road to Chaos by Time-Asymmetric Hebbian Learning in Recurrent Neural Networks -- Molter et al. 19 (1): 80 -- ...
		The Road to Chaos by Time-Asymmetric Hebbian Learning in Recurrent Neural Networks -- Molter et al.
		The Road to Chaos by Time-Asymmetric Hebbian Learning in Recurrent Neural Networks
		It is still possible to observe the traces of the learned
	neco.mitpress.org /cgi/content/abstract/19/1/80 (308 words)

	IEEE Xplore - Login
		Summary:The design and performance of a Hebbian learning based neural network is presented in this work.
		In situ analog learning was employed, thus computing the synaptic weight changes continuously during the normal operation of the artificial neural network (ANN).
		The complexity of a synapse is minimized by using a novel device called the Programmable Metallization Cell (PMC).
	ieeexplore.ieee.org /iel4/5627/15080/00703888.pdf?isnumber=15080&prod=CNF&arnumber=703888&arSt=33&ared=36+vol.3&arAuthor=Swaroop%2C+B.%3B+West%2C+W.C.%3B+Martinez%2C+G.%3B+Kozicki%2C+M.N.%3B+Akers%2C+L.A. (258 words)

Try your search on: Qwika (all wikis)