Patents by Inventor Timoleon Moraitis
Timoleon Moraitis has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 11823038Abstract: A computer-implemented method for managing datasets of a storage system is provided, wherein the datasets have respective sets of metadata, the method including: successively feeding first sets of metadata to a spiking neural network (SNN), the first sets of metadata fed corresponding to datasets of the storage system that are labeled with respect to classes they belong to, so as to be associated with class labels, for the SNN to learn representations of said classes in terms of connection weights that weight the metadata fed; successively feeding second sets of metadata to the SNN, the second sets of metadata corresponding to unlabeled datasets of the storage system, for the SNN to infer class labels for the unlabeled datasets, based on the second sets of metadata fed and the representations learned; and managing datasets in the storage system, based on class labels of the datasets, these including the inferred class labels.Type: GrantFiled: June 22, 2018Date of Patent: November 21, 2023Assignee: International Business Machines CorporationInventors: Giovanni Cherubini, Timoleon Moraitis, Abu Sebastian, Vinodh Venkatesan
-
Patent number: 11727250Abstract: A computer device, a non-transitory computer storage medium, and a computer-implemented method of pattern recognition utilizing an elastic clustering algorithm. A sequence of input datapoints are assigned to a particular cluster of K clusters based on a distance from a centroid k representing a center of the particular cluster. The centroid k in each of the K clusters is shifted from a first position to a second position closer than the first position from the sequence of input datapoints. A location of the centroid k in each of the K clusters is relaxed from the second position toward an equilibrium point in the particular cluster of the K clusters. The relaxing of the location of the centroid k occurs according to an elasticity pull factor based on a distance between the centroid k of the particular cluster at a time t.Type: GrantFiled: September 6, 2019Date of Patent: August 15, 2023Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Timoleon Moraitis, Abu Sebastian
-
Patent number: 11615298Abstract: A circuit implementing a spiking neural network that includes a learning component that can learn from temporal correlations in the spikes regardless of correlations in the rates. In some embodiments, the learning component comprises a rate-discounting component. In some embodiments, the learning rule computes a rate-normalized covariance (normcov) matrix, detects clusters in this matrix, and sets the synaptic weights according to these clusters. In some embodiments, a synapse with a long-term plasticity rule has an efficacy that is composed by a weight and a fatiguing component. In some embodiments, A Hebbian plasticity component modifies the weight component and a short-term fatigue plasticity component modifies the fatiguing component. The fatigue component increases with increases in the presynaptic spike rate. In some embodiments, the fatigue component increases are implemented in a spike-based manner.Type: GrantFiled: March 11, 2022Date of Patent: March 28, 2023Assignee: Samsung Electronics Co., Ltd.Inventors: Wabe W. Koelmans, Timoleon Moraitis, Abu Sebastian, Tomas Tuma
-
Patent number: 11397544Abstract: A neuromorphic memory element comprises a memristor, a plurality of the neuromorphic memory elements and a method for operating the same may be provided. The memristor comprises an input signal terminal, an output signal terminal, and a control signal terminal, and a memristive active channel comprising a phase change material. The memristive active channel extends longitudinal between the input signal terminal and the output signal terminal, and a control signal voltage at the control signal terminal is configured to represent volatile biological neural processes of the neuromorphic memory element, and a bias voltage between the input signal terminal and the output signal terminal is configured to represent non-volatile biological neural processes of the neuromorphic memory element.Type: GrantFiled: November 10, 2020Date of Patent: July 26, 2022Assignee: International Business Machines CorporationInventors: Ghazi Sarwat Syed, Abu Sebastian, Timoleon Moraitis, Benedikt Kersting
-
Publication number: 20220198252Abstract: A circuit implementing a spiking neural network that includes a learning component that can learn from temporal correlations in the spikes regardless of correlations in the rates. In some embodiments, the learning component comprises a rate-discounting component. In some embodiments, the learning rule computes a rate-normalized covariance (normcov) matrix, detects clusters in this matrix, and sets the synaptic weights according to these clusters. In some embodiments, a synapse with a long-term plasticity rule has an efficacy that is composed by a weight and a fatiguing component. In some embodiments, A Hebbian plasticity component modifies the weight component and a short-term fatigue plasticity component modifies the fatiguing component. The fatigue component increases with increases in the presynaptic spike rate. In some embodiments, the fatigue component increases are implemented in a spike-based manner.Type: ApplicationFiled: March 11, 2022Publication date: June 23, 2022Applicant: Samsung Electronics Co., Ltd.Inventors: Wabe W. Koelmans, Timoleon Moraitis, Abu Sebastian, Tomas Tuma
-
Patent number: 11354572Abstract: The present disclosure relates to a method of generating spikes by a neuron of a spiking neural network. The method comprises generating at each time, wherein the spike generation encodes at each time instant at least two variable values at the neuron. Synaptic weights may be optimized for a spike train generated by a given presynaptic neuron of a spiking neural network, wherein the spike train being indicative of features of at least one timescale.Type: GrantFiled: December 5, 2018Date of Patent: June 7, 2022Assignee: International Business Machines CorporationInventors: Timoleon Moraitis, Abu Sebastian
-
Publication number: 20220147271Abstract: A neuromorphic memory element comprises a memristor, a plurality of the neuromorphic memory elements and a method for operating the same may be provided. The memristor comprises an input signal terminal, an output signal terminal, and a control signal terminal, and a memristive active channel comprising a phase change material. The memristive active channel extends longitudinal between the input signal terminal and the output signal terminal, and a control signal voltage at the control signal terminal is configured to represent volatile biological neural processes of the neuromorphic memory element, and a bias voltage between the input signal terminal and the output signal terminal is configured to represent non-volatile biological neural processes of the neuromorphic memory element.Type: ApplicationFiled: November 10, 2020Publication date: May 12, 2022Inventors: Ghazi Sarwat Syed, Abu Sebastian, Timoleon Moraitis, Benedikt Kersting
-
Patent number: 11308382Abstract: Neuromorphic synapse apparatus is provided comprising a synaptic device and a control signal generator. The synaptic device comprises a memory element, disposed between first and second terminals, for conducting a signal between those terminals with an efficacy which corresponds to a synaptic weight in a read mode of operation, and a third terminal operatively coupled to the memory element. The memory element has a non-volatile characteristic, which is programmable to vary the efficacy in response to programming signals applied via the first and second terminals in a write mode of operation, and a volatile characteristic which is controllable to vary the efficacy in response to control signals applied to the third terminal. The control signal generator is responsive to input signals and is adapted to apply control signals to the third terminal in the read and write modes, in dependence on the input signals, to implement predetermined synaptic dynamics.Type: GrantFiled: August 25, 2017Date of Patent: April 19, 2022Assignee: International Business Machines CorporationInventors: Wabe W. Koelmans, Timoleon Moraitis, Abu Sebastian
-
Patent number: 11308387Abstract: A circuit implementing a spiking neural network that includes a learning component that can learn from temporal correlations in the spikes regardless of correlations in the rates. In some embodiments, the learning component comprises a rate-discounting component. In some embodiments, the learning rule computes a rate-normalized covariance (normcov) matrix, detects clusters in this matrix, and sets the synaptic weights according to these clusters. In some embodiments, a synapse with a long-term plasticity rule has an efficacy that is composed by a weight and a fatiguing component. In some embodiments, A Hebbian plasticity component modifies the weight component and a short-term fatigue plasticity component modifies the fatiguing component. The fatigue component increases with increases in the presynaptic spike rate. In some embodiments, the fatigue component increases are implemented in a spike-based manner.Type: GrantFiled: May 9, 2017Date of Patent: April 19, 2022Assignee: Samsung Electronics Co., Ltd.Inventors: Wabe W. Koelmans, Timoleon Moraitis, Abu Sebastian, Tomas Tuma
-
Patent number: 11238333Abstract: A circuit implementing a spiking neural network that includes a learning component that can learn from temporal correlations in the spikes regardless of correlations in the rates. In some embodiments, the learning component comprises a rate-discounting component. In some embodiments, the learning rule computes a rate-normalized covariance (normcov) matrix, detects clusters in this matrix, and sets the synaptic weights according to these clusters. In some embodiments, a synapse with a long-term plasticity rule has an efficacy that is composed by a weight and a fatiguing component. In some embodiments, A Hebbian plasticity component modifies the weight component and a short-term fatigue plasticity component modifies the fatiguing component. The fatigue component increases with increases in the presynaptic spike rate. In some embodiments, the fatigue component increases are implemented in a spike-based manner.Type: GrantFiled: April 10, 2019Date of Patent: February 1, 2022Assignee: Samsung Electronics Co., Ltd.Inventors: Wabe W. Koelmans, Timoleon Moraitis, Abu Sebastian, Tomas Tuma
-
Patent number: 11200484Abstract: Methods and apparatus are provided for implementing propagation of probability distributions of random variables over a factor graph. Such a method includes providing a spiking neural network, having variable nodes interconnected with factor nodes, corresponding to the factor graph. Each of the nodes comprises a set of neurons configured to implement computational functionality of that node. The method further comprises generating, for each of a set of the random variables, at least one spike signal in which the probability of a possible value of that variable is encoded via the occurrence of spikes in the spike signal, and supplying the spike signals for the set of random variables as inputs to the neural network at respective variable nodes. The probability distributions are propagated via the occurrence of spikes in signals propagated through the neural network.Type: GrantFiled: September 6, 2018Date of Patent: December 14, 2021Assignee: International Business Machines CorporationInventors: Giovanni Cherubini, Timoleon Moraitis, Abu Sebastian
-
Publication number: 20210073616Abstract: A computer device, a non-transitory computer storage medium, and a computer-implemented method of pattern recognition utilizing an elastic clustering algorithm. A sequence of input datapoints are assigned to a particular cluster of K clusters based on a distance from a centroid k representing a center of the particular cluster. The centroid kin each of the K clusters is shifted from a first position to a second position closer than the first position from the sequence of input datapoints. A location of the centroid k in each of the K clusters is relaxed from the second position toward an equilibrium point in the particular cluster of the K clusters. The relaxing of the location of the centroid k occurs according to an elasticity pull factor based on a distance between the centroid k of the particular cluster at a time t.Type: ApplicationFiled: September 6, 2019Publication date: March 11, 2021Inventors: Timoleon Moraitis, Abu Sebastian
-
Publication number: 20200184325Abstract: The present disclosure relates to a method of generating spikes by a neuron of a spiking neural network. The method comprises generating at each time, wherein the spike generation encodes at each time instant at least two variable values at the neuron. Synaptic weights may be optimized for a spike train generated by a given presynaptic neuron of a spiking neural network, wherein the spike train being indicative of features of at least one timescale.Type: ApplicationFiled: December 5, 2018Publication date: June 11, 2020Inventors: Timoleon Moraitis, Abu Sebastian
-
Publication number: 20200082251Abstract: Methods and apparatus are provided for implementing propagation of probability distributions of random variables over a factor graph. Such a method includes providing a spiking neural network, having variable nodes interconnected with factor nodes, corresponding to the factor graph. Each of the nodes comprises a set of neurons configured to implement computational functionality of that node. The method further comprises generating, for each of a set of the random variables, at least one spike signal in which the probability of a possible value of that variable is encoded via the occurrence of spikes in the spike signal, and supplying the spike signals for the set of random variables as inputs to the neural network at respective variable nodes. The probability distributions are propagated via the occurrence of spikes in signals propagated through the neural network.Type: ApplicationFiled: September 6, 2018Publication date: March 12, 2020Inventors: Giovanni Cherubini, Timoleon Moraitis, Abu Sebastian
-
Publication number: 20190392303Abstract: A computer-implemented method for managing datasets of a storage system is provided, wherein the datasets have respective sets of metadata, the method including: successively feeding first sets of metadata to a spiking neural network (SNN), the first sets of metadata fed corresponding to datasets of the storage system that are labeled with respect to classes they belong to, so as to be associated with class labels, for the SNN to learn representations of said classes in terms of connection weights that weight the metadata fed; successively feeding second sets of metadata to the SNN, the second sets of metadata corresponding to unlabeled datasets of the storage system, for the SNN to infer class labels for the unlabeled datasets, based on the second sets of metadata fed and the representations learned; and managing datasets in the storage system, based on class labels of the datasets, these including the inferred class labels.Type: ApplicationFiled: June 22, 2018Publication date: December 26, 2019Inventors: Giovanni Cherubini, Timoleon Moraitis, Abu Sebastian, Vinodh Venkatesan
-
Publication number: 20190236443Abstract: A circuit implementing a spiking neural network that includes a learning component that can learn from temporal correlations in the spikes regardless of correlations in the rates. In some embodiments, the learning component comprises a rate-discounting component. In some embodiments, the learning rule computes a rate-normalized covariance (normcov) matrix, detects clusters in this matrix, and sets the synaptic weights according to these clusters. In some embodiments, a synapse with a long-term plasticity rule has an efficacy that is composed by a weight and a fatiguing component. In some embodiments, A Hebbian plasticity component modifies the weight component and a short-term fatigue plasticity component modifies the fatiguing component. The fatigue component increases with increases in the presynaptic spike rate. In some embodiments, the fatigue component increases are implemented in a spike-based manner.Type: ApplicationFiled: April 10, 2019Publication date: August 1, 2019Inventors: Wabe W. Koelmans, Timoleon Moraitis, Abu Sebastian, Tomas Tuma
-
Publication number: 20190065929Abstract: Neuromorphic synapse apparatus is provided comprising a synaptic device and a control signal generator. The synaptic device comprises a memory element, disposed between first and second terminals, for conducting a signal between those terminals with an efficacy which corresponds to a synaptic weight in a read mode of operation, and a third terminal operatively coupled to the memory element. The memory element has a non-volatile characteristic, which is programmable to vary the efficacy in response to programming signals applied via the first and second terminals in a write mode of operation, and a volatile characteristic which is controllable to vary the efficacy in response to control signals applied to the third terminal. The control signal generator is responsive to input signals and is adapted to apply control signals to the third terminal in the read and write modes, in dependence on the input signals, to implement predetermined synaptic dynamics.Type: ApplicationFiled: August 25, 2017Publication date: February 28, 2019Inventors: Wabe W. Koelmans, Timoleon Moraitis, Abu Sebastian
-
Publication number: 20180330227Abstract: A circuit implementing a spiking neural network that includes a learning component that can learn from temporal correlations in the spikes regardless of correlations in the rates. In some embodiments, the learning component comprises a rate-discounting component. In some embodiments, the learning rule computes a rate-normalized covariance (normcov) matrix, detects clusters in this matrix, and sets the synaptic weights according to these clusters. In some embodiments, a synapse with a long-term plasticity rule has an efficacy that is composed by a weight and a fatiguing component. In some embodiments, A Hebbian plasticity component modifies the weight component and a short-term fatigue plasticity component modifies the fatiguing component. The fatigue component increases with increases in the presynaptic spike rate. In some embodiments, the fatigue component increases are implemented in a spike-based manner.Type: ApplicationFiled: May 9, 2017Publication date: November 15, 2018Inventors: Wabe W. Koelmans, Timoleon Moraitis, Abu Sebastian, Tomas Tuma
-
Publication number: 20180330228Abstract: A circuit implementing a spiking neural network that includes a learning component that can learn from temporal correlations in the spikes regardless of correlations in the rates. In some embodiments, the learning component comprises a rate-discounting component. In some embodiments, the learning rule computes a rate-normalized covariance (normcov) matrix, detects clusters in this matrix, and sets the synaptic weights according to these clusters. In some embodiments, a synapse with a long-term plasticity rule has an efficacy that is composed by a weight and a fatiguing component. In some embodiments, A Hebbian plasticity component modifies the weight component and a short-term fatigue plasticity component modifies the fatiguing component. The fatigue component increases with increases in the presynaptic spike rate. In some embodiments, the fatigue component increases are implemented in a spike-based manner.Type: ApplicationFiled: February 5, 2018Publication date: November 15, 2018Inventors: Wabe W. Koelmans, Timoleon Moraitis, Abu Sebastian, Tomas Tuma