Patents by Inventor Jeffrey L. McKinstry
Jeffrey L. McKinstry 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: 11823054Abstract: Learned step size quantization in artificial neural network is provided. In various embodiments, a system comprises an artificial neural network and a computing node. The artificial neural network comprises: a quantizer having a configurable step size, the quantizer adapted to receive a plurality of input values and quantize the plurality of input values according to the configurable step size to produce a plurality of quantized input values, at least one matrix multiplier configured to receive the plurality of quantized input values from the quantizer and to apply a plurality of weights to the quantized input values to determine a plurality of output values having a first precision, and a multiplier configured to scale the output values to a second precision.Type: GrantFiled: February 20, 2020Date of Patent: November 21, 2023Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Steve Esser, Jeffrey L. McKinstry, Deepika Bablani, Rathinakumar Appuswamy, Dharmendra S. Modha
-
Publication number: 20210264279Abstract: Learned step size quantization in artificial neural network is provided. In various embodiments, a system comprises an artificial neural network and a computing node. The artificial neural network comprises: a quantizer having a configurable step size, the quantizer adapted to receive a plurality of input values and quantize the plurality of input values according to the configurable step size to produce a plurality of quantized input values, at least one matrix multiplier configured to receive the plurality of quantized input values from the quantizer and to apply a plurality of weights to the quantized input values to determine a plurality of output values having a first precision, and a multiplier configured to scale the output values to a second precision.Type: ApplicationFiled: February 20, 2020Publication date: August 26, 2021Inventors: Steve Esser, Jeffrey L. McKinstry, Deepika Bablani, Rathinakumar Appuswamy, Dharmendra S. Modha
-
Publication number: 20130274919Abstract: A mobile brain-based device BBD includes a mobile base equipped with sensors and effectors (Neurally Organized Mobile Adaptive Device or NOMAD), which is guided by a simulated nervous system that is an analogue of cortical and sub-cortical areas of the brain required for visual processing, decision-making, reward, and motor responses. The brain-based device BBD learns to discriminate among multiple objects with shared visual features, and associated “target” objects with innately preferred auditory cues. The brain-based device BBD is moveable, in a rich real-world environment involving continual changes in the size and location of visual stimuli due to self-generated or autonomous, movement, and shows that reentrant connectivity and dynamic synchronization provide an effective mechanism for binding the features of visual objects so as to reorganize object features such as color, shape and motion while distinguishing distinct objects in the environment.Type: ApplicationFiled: June 11, 2013Publication date: October 17, 2013Inventors: Anil K. Seth, Jeffrey L. McKinstry, Gerald M. Edelman, Jeffrey L. Krichmar
-
Publication number: 20120173020Abstract: A mobile brain-based device BBD includes a mobile base equipped with sensors and effectors (Neurally Organized Mobile Adaptive Device or NOMAD), which is guided by a simulated nervous system that is an analogue of cortical and sub-cortical areas of the brain required for visual processing, decision-making, reward, and motor responses. The brain-based device BBD learns to discriminate among multiple objects with shared visual features, and associated “target” objects with innately preferred auditory cues. The brain-based device BBD is moveable, in a rich real-world environment involving continual changes in the size and location of visual stimuli due to self-generated or autonomous, movement, and shows that reentrant connectivity and dynamic synchronization provide an effective mechanism for binding the features of visual objects so as to reorganize object features such as color, shape and motion while distinguishing distinct objects in the environment.Type: ApplicationFiled: November 30, 2011Publication date: July 5, 2012Applicant: NEUROSCIENCES RESEARCH FOUNDATION, INC.Inventors: Anil K. Seth, Jeffrey L. McKinstry, Gerald M. Edelman, Jeffrey L. Krichmar
-
Patent number: 8131658Abstract: A mobile brain-based device (BBD) includes a mobile platform with sensors and effectors, which is guided by a simulated nervous system that is an analogue of the cerebellar areas of the brain used for predictive motor control to determine interaction with a real-world environment. The simulated nervous system has neural areas including precerebellum nuclei (PN), Purkinje cells (PC), deep cerebellar nuclei (DCN) and an inferior olive (IO) for predicting turn and velocity control of the BBD during movement in a real-world environment. The BBD undergoes training and testing, and the simulated nervous system learns and performs control functions, based on a delayed eligibility trace learning rule.Type: GrantFiled: October 28, 2010Date of Patent: March 6, 2012Assignee: Neurosciences Research Foundation, Inc.Inventors: Jeffrey L. McKinstry, Gerald M. Edelman, Jeffrey L. Krichmar
-
Publication number: 20110184556Abstract: A mobile brain-based device BBD includes a mobile base equipped with sensors and effectors (Neurally Organized Mobile Adaptive Device or NOMAD), which is guided by a simulated nervous system that is an analogue of cortical and sub-cortical areas of the brain required for visual processing, decision-making, reward, and motor responses. These simulated cortical and sub-cortical areas are reentrantly connected and each area contains neuronal units representing both the mean activity level and the relative timing of the activity of groups of neurons. The brain-based device BBD learns to discriminate among multiple objects with shared visual features, and associated “target” objects with innately preferred auditory cues. Globally distributed neuronal circuits that correspond to distinct objects in the visual field of NOMAD 10 are activated. These circuits, which are constrained by a reentrant neuroanatomy and modulated by behavior and synaptic plasticity, result in successful discrimination of objects.Type: ApplicationFiled: April 10, 2009Publication date: July 28, 2011Applicant: Neurosciences Research Foundation, Inc.Inventors: Anil K. Seth, Jeffrey L. McKinstry, Gerald M. Edelman, Jeffrey L. Krichmar
-
Publication number: 20110047109Abstract: A mobile brain-based device (BBD) includes a mobile platform with sensors and effectors, which is guided by a simulated nervous system that is an analogue of the cerebellar areas of the brain used for predictive motor control to determine interaction with a real-world environment. The simulated nervous system has neural areas including precerebellum nuclei (PN), Purkinje cells (PC), deep cerebellar nuclei (DCN) and an inferior olive (IO) for predicting turn and velocity control of the BBD during movement in a real-world environment. The BBD undergoes training and testing, and the simulated nervous system learns and performs control functions, based on a delayed eligibility trace learning rule.Type: ApplicationFiled: October 28, 2010Publication date: February 24, 2011Applicant: NEUROSCIENCES RESEARCH FOUNDATION, INC.Inventors: Jeffrey L. McKinstry, Gerald M. Edelman, Jeffrey L. Krichmar
-
Patent number: 7827124Abstract: A mobile brain-based device (BBD) includes a mobile platform with sensors and effectors, which is guided by a simulated nervous system that is an analogue of the cerebellar areas of the brain used for predictive motor control to determine interaction with a real-world environment. The simulated nervous system has neural areas including precerebellum nuclei (PN), Purkinje cells (PC), deep cerebellar nuclei (DCN) and an inferior olive (IO) for predicting turn and velocity control of the BBD during movement in a real-world environment. The BBD undergoes training and testing, and the simulated nervous system learns and performs control functions, based on a delayed eligibility trace learning rule.Type: GrantFiled: December 27, 2006Date of Patent: November 2, 2010Assignee: Neurosciences Research Foundation, Inc.Inventors: Jeffrey L. McKinstry, Gerald M. Edelman, Jeffrey L. Krichmar
-
Patent number: 7519452Abstract: A mobile brain-based device BBD includes a mobile base equipped with sensors and effectors (Neurally Organized Mobile Adaptive Device or NOMAD), which is guided by a simulated nervous system that is an analogue of cortical and sub-cortical areas of the brain required for visual processing, decision-making, reward, and motor responses. These simulated cortical and sub-cortical areas are reentrantly connected and each area contains neuronal units representing both the mean activity level and the relative timing of the activity of groups of neurons. The brain-based device BBD learns to discriminate among multiple objects with shared visual features, and associated “target” objects with innately preferred auditory cues. Globally distributed neuronal circuits that correspond to distinct objects in the visual field of NOMAD 10 are activated. These circuits, which are constrained by a reentrant neuroanatomy and modulated by behavior and synaptic plasticity, result in successful discrimination of objects.Type: GrantFiled: April 13, 2005Date of Patent: April 14, 2009Assignee: Neurosciences Research Foundation, Inc.Inventors: Anil K. Seth, Jeffrey L. McKinstry, Gerald M. Edelman, Jeffrey L. Krichmar