Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 17 of 17 for “"Hebbian learning"”.
-
Self-orthogonalizing strategies for enhancing Hebbian learning in recurrent neural networks
… recurrent, and still learns by prescriptive Hebbian learning, but the hidden neurons give it power and flexibility which were not available in Hopfield’s original network. The key to the success of the model is that it uses the emerging structure of its own memory space to establish a pattern …
-
Improving Liquid State Machines Through Iterative Refinement of the Reservoir
… to create a more effective one. First, we apply Hebbian learning to LSMs by building the liquid with spike-time dependant plasticity (STDP) synapses. Second, we create an eligibility based reinforcement learning algorithm for synaptic development. Third, we apply principles of Hebbian learning …
-
Towards adaptive neural networks: Bio-inspired principles for functional and structural plasticity
… we attempt to imitate this process by employing Hebbian Learning, a model of plasticity, in ANNs. This model is inspired by Hebb’s theory, which can be summarized as: “If one neuron actively contributes to the firing of a second neuron, their connection strengthens”. In particular, we employed …
-
Dynamics and learning in recurrent neural networks
This thesis is a study of dynamics and learning in recurrent neural networks. Many computations of neural systems are carried out through a network of a large number of neurons. With massive feedback connections among these neurons, a study of its dynamics is necessary in order to understand the …
-
Dynamics of adaptive recurrent neural networks
… The plasticity rule is chosen from the class of Hebbian learning rules, in which the synaptic connection between two neurons evolves continuously as a function of their correlation in the recent past. Initially an analysis of networks of two neurons is presented, which exhibit relaxation …
-
Evolving Neural Networks with HyperNEAT and Online Training
… through strategic application of online learning. Several methods are proposed and explored. All methodologies are tested using a team gathering task. A simulated environment is setup with gathering robots that must locate resources and work together to carry the resources back to a …
-
Investigating neuronal network dynamics : scale-invariance, preferred firing rates, and plasticity via phase-shift encoding
… capabilities. Targeted stimulation based on Hebbian learning rules with Granger causality analysis was used to evaluate pre-synaptic and post-synaptic relationships. Distinct firing patterns emerged from the baseline and Poisson stimulations via Fourier transform analysis, suggesting stable, …
-
Modelling metrical flux: an adaptive frequency neural network for expressive rhythmic perception and prediction
… perception with GFNNs can improve a machine learning music model. However, it is also discovered that GFNNs perform poorly when dealing with tempo changes in the stimulus. Therefore, a novel Adaptive Frequency Neural Network (AFNN) is introduced; extending the GFNN with a Hebbian learning …
-
Boolean Weightless Neural Network Architectures
… is further enhanced by the addition of a new learning paradigm, that of non-Hebbian Learning. This new method concentrates on the association of ‘dis-similarity’, believing this is as important as areas of similarity. Image processing using hardware weightless neural networks is investigated …
-
Neurocomputational Methods for Autonomous Cognitive Control
… human cerebral cortex and biologically-plausible Hebbian learning, neural regions that each serve as an attractor network able to learn sequences, and neural regions that not only learn to exchange information but also to modulate the functions of other regions. The resultant networks have …
-
An Electrophysiological Investigation of Embodied Language Processing
… our personal experiences in the world, through Hebbian learning. The findings of our final experiment supported this argument, indicating that the conceptual representation of objects, and the actions associated with their use, were developed during the participants’ previous experience of using …
-
Modelling and tracking objects with a topology preserving self-organising neural network
… models should be automatically acquired via a learning scheme that enables the acquisition of detailed behavioural knowledge only from topological and temporal observation. The research described in this thesis is motivated by a desire to provide a framework for the unsupervised acquisition and …
-
Approaches to Understanding the Function of Intrinsic Activity and its Relationship to Task-evoked Activity in the Human Brain
… by neural activity evoked by a task through a Hebbian learning process. This thesis aims to reveal correspondences between intrinsic activity and task-evoked activity to better understand the nature and function of intrinsic brain activity. We measured in human visual cortex the blood oxygen …
-
Image Compression and Channel Error Correction using Neurally-Inspired Network Models
… DNN implemented with the Levenberg-Marguardt learning algorithm is proposed and implemented for image compression. I demonstrate experimentally that the DNN not only provides better quality reconstructed images but also requires less computational capacity as compared to DCT Zonal coding, DCT …
-
Inference and Learning in Spiking Neural Networks for Neuromorphic Systems
… algorithms for training. Biologically plausible learning mechanism spike-timing-dependent plasticity (STDP) and its variants are local in synapses and time but are unstable during training and difficult to train multi-layer SNNs.</p><p>To better exploit the energy-saving features such as spike …
-
Inference And Learning In Spiking Neural Networks For Neuromorphic Systems
… algorithms for training. Biologically plausible learning mechanism spike-timing-dependent plasticity (STDP) and its variants are local in synapses and time but are unstable during training and difficult to train multi-layer SNNs.</p><p>To better exploit the energy-saving features such as spike …
-
Understanding language and attention: brain-based model and neurophysiological experiments
… early word acquisition processes by means of a Hebbian correlation learning rule (which reflects known synaptic plasticity mechanisms of the neocortex). The network was “taught” to associate pairs of auditory and articulatory activation patterns, simulating activity due to perception and …