The Experts below are selected from a list of 1197 Experts worldwide ranked by ideXlab platform
Torsten Lehmann - One of the best experts on this subject based on the ideXlab platform.
-
Biologically-Inspired On-Chip Learning in Pulsed Neural Networks
Analog Integrated Circuits and Signal Processing, 1999Co-Authors: Torsten Lehmann, R. WoodburnAbstract:Self-learning chips to implement many popular ANN (artificial neural network) algorithms are very difficult to design. We explain why this is so and say what lessons previous work teaches us in the design of self-learning systems. We offer a contribution to the “biologically-inspired” approach, explaining what we mean by this term and providing an example of a robust, self-learning design that can solve Simple Classical-Conditioning tasks. We give details of the design of individual circuits to perform component functions, which can then be combined into a network to solve the task. We argue that useful conclusions as to the future of on-chip learning can be drawn from this work.
-
Classical Conditioning with pulsed integrated neural networks: circuits and system
IEEE Transactions on Circuits and Systems II: Analog and Digital Signal Processing, 1998Co-Authors: Torsten LehmannAbstract:In this paper, we investigate on-chip learning for pulsed, integrated neural networks. We discuss the implementational problems the technology imposes on learning systems, and we find that a biologically inspired approach using Simple circuit structures is most likely to bring success. We develop a suitable learning algorithm-a continuous-time version of a temporal differential Hebbian learning algorithm for pulsed neural systems with nonlinear synapses-as well as circuits for the electronic implementation. Measurements from an experimental CMOS chip are presented. Finally, we use our test chip to solve Simple Classical Conditioning tasks, thus verifying the design methodologies put forward in the paper.
-
ECCOPUNCH: the Edinburgh Classical Conditioning pulsed neural chip
Proceedings of 1997 IEEE International Symposium on Circuits and Systems. Circuits and Systems in the Information Age ISCAS '97, 1Co-Authors: Torsten LehmannAbstract:In this paper, we present experimental results from the critical circuit structures on the Edinburgh Classical Conditioning Pulsed Neural Chip. Being inspired from psycho-biological modelling, this chip successfully implements a continuous time version of a differential Hebbian learning algorithm for pulsed neural systems with non-linear synapses. The chip can solve Simple Classical Conditioning tasks and the working chip verifies the design methodologies put forward in previous papers.
-
On-chip learning in pulsed silicon neural networks
Proceedings of 1997 IEEE International Symposium on Circuits and Systems. Circuits and Systems in the Information Age ISCAS '97, 1Co-Authors: Torsten Lehmann, R. Woodburn, A.f. MurrayAbstract:Self-learning chips to implement conventional ANN (artificial neural network) algorithms are very difficult to design and unconvincing in their results. We explain why this is so and say what lessons previous work teaches us in the design of self-learning systems. We offer an alternative, 'biologically-inspired' approach, explaining what we mean by this term and providing an example of a robust, self-learning design which can solve Simple Classical-Conditioning tasks.
D. Van Der Kooy - One of the best experts on this subject based on the ideXlab platform.
-
Acquisition of conditional discriminations in hippocampal lesioned and decorticated rats: evidence for learning that is separate from both Simple Classical Conditioning and configural learning.
Behavioral neuroscience, 1994Co-Authors: Darlene M. Skinner, Gerard M. Martin, Carolyn W. Harley, Bryan Kolb, Adora Pridgar, Antoine Bechara, D. Van Der KooyAbstract:This study examined whether hippocampal or neocortical lesions would impair acquisition of a discrimination task using taste aversions. Rats were injected with a drug 15 min before a flavored solution-lithium chloride pairing. On alternate days, vehicle injections preceded and followed access to the same flavored solution. Rats learned to consume significantly more of the flavored solution after vehicle injections than after drug injections. Rats with hippocampal lesions or neonatal decortication performed as well as controls. Rats with hippocampal lesions also learned a similar task in which visual and textural cues predicted whether access to a flavored solution would be followed by an injection of lithium chloride or vehicle. However, these hippocampal lesions did impair performance in the Morris water task. Occasion setting may involve a type of learning dissociated from both Simple Classical Conditioning and configural learning.
Bernard G. Schreurs - One of the best experts on this subject based on the ideXlab platform.
-
A functional anatomical study of associative learning in humans
Proceedings of the National Academy of Sciences of the United States of America, 1994Co-Authors: Susan E. Molchan, Trey Sunderland, Anthony R. Mcintosh, Peter Herscovitch, Bernard G. SchreursAbstract:Abstract The purpose of the study was to map the functional neuroanatomy of Simple associative learning in humans. Eyeblink Conditioning was studied in eight normal volunteers using positron emission tomography and H215O. Regional cerebral blood flow was assessed during three sequential phases: (i) explicitly unpaired presentations of the unconditioned stimulus (air puff to the right eye) and conditioned stimulus (binaural tone), (ii) paired presentations of the two stimuli (associative learning), and (iii) presentation of the conditioned stimulus alone. During associative learning, relative to the unpaired phase, blood flow was significantly increased in primary auditory and left posterior cingulate cortices and significantly decreased in areas of the right cerebellar, right prefrontal, right parietal, and insular cortices and right neostriatum. The lateralization of the changes may relate to the functional organization of memory and learning processes in the brain. The activation in primary auditory cortex is an example, using a neuroimaging technique, of a learning-related change in primary sensory cortex in humans. The changes in areas such as the cerebellum, prefrontal cortex, and neostriatum provide support for their roles in associative learning as proposed by animal models. Moreover, these findings show that in humans, even Simple Classical Conditioning involves distributed changes in multiple neural systems.
Darlene M. Skinner - One of the best experts on this subject based on the ideXlab platform.
-
Acquisition of conditional discriminations in hippocampal lesioned and decorticated rats: evidence for learning that is separate from both Simple Classical Conditioning and configural learning.
Behavioral neuroscience, 1994Co-Authors: Darlene M. Skinner, Gerard M. Martin, Carolyn W. Harley, Bryan Kolb, Adora Pridgar, Antoine Bechara, D. Van Der KooyAbstract:This study examined whether hippocampal or neocortical lesions would impair acquisition of a discrimination task using taste aversions. Rats were injected with a drug 15 min before a flavored solution-lithium chloride pairing. On alternate days, vehicle injections preceded and followed access to the same flavored solution. Rats learned to consume significantly more of the flavored solution after vehicle injections than after drug injections. Rats with hippocampal lesions or neonatal decortication performed as well as controls. Rats with hippocampal lesions also learned a similar task in which visual and textural cues predicted whether access to a flavored solution would be followed by an injection of lithium chloride or vehicle. However, these hippocampal lesions did impair performance in the Morris water task. Occasion setting may involve a type of learning dissociated from both Simple Classical Conditioning and configural learning.
Susan E. Molchan - One of the best experts on this subject based on the ideXlab platform.
-
A functional anatomical study of associative learning in humans
Proceedings of the National Academy of Sciences of the United States of America, 1994Co-Authors: Susan E. Molchan, Trey Sunderland, Anthony R. Mcintosh, Peter Herscovitch, Bernard G. SchreursAbstract:Abstract The purpose of the study was to map the functional neuroanatomy of Simple associative learning in humans. Eyeblink Conditioning was studied in eight normal volunteers using positron emission tomography and H215O. Regional cerebral blood flow was assessed during three sequential phases: (i) explicitly unpaired presentations of the unconditioned stimulus (air puff to the right eye) and conditioned stimulus (binaural tone), (ii) paired presentations of the two stimuli (associative learning), and (iii) presentation of the conditioned stimulus alone. During associative learning, relative to the unpaired phase, blood flow was significantly increased in primary auditory and left posterior cingulate cortices and significantly decreased in areas of the right cerebellar, right prefrontal, right parietal, and insular cortices and right neostriatum. The lateralization of the changes may relate to the functional organization of memory and learning processes in the brain. The activation in primary auditory cortex is an example, using a neuroimaging technique, of a learning-related change in primary sensory cortex in humans. The changes in areas such as the cerebellum, prefrontal cortex, and neostriatum provide support for their roles in associative learning as proposed by animal models. Moreover, these findings show that in humans, even Simple Classical Conditioning involves distributed changes in multiple neural systems.