Patents by Inventor Bipin Rajendran

Bipin Rajendran 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: 10810487
    Abstract: A reconfigurable neural network circuit is provided. The reconfigurable neural network circuit comprises an electronic synapse array including multiple synapses interconnecting a plurality of digital electronic neurons. Each neuron comprises an integrator that integrates input spikes and generates a signal when the integrated inputs exceed a threshold. The circuit further comprises a control module for reconfiguring the synapse array. The control module comprises a global final state machine that controls timing for operation of the circuit, and a priority encoder that allows spiking neurons to sequentially access the synapse array.
    Type: Grant
    Filed: August 22, 2016
    Date of Patent: October 20, 2020
    Assignee: International Business Machines Corporation
    Inventors: Bernard V. Brezzo, Leland Chang, Steven K. Esser, Daniel J. Friedman, Yong Liu, Dharmendra S. Modha, Robert K. Montoye, Bipin Rajendran, Jae-sun Seo, Jose A. Tierno
  • Patent number: 10628732
    Abstract: A reconfigurable neural network circuit is provided. The reconfigurable neural network circuit comprises an electronic synapse array including multiple synapses interconnecting a plurality of digital electronic neurons. Each neuron comprises an integrator that integrates input spikes and generates a signal when the integrated inputs exceed a threshold. The circuit further comprises a control module for reconfiguring the synapse array. The control module comprises a global final state machine that controls timing for operation of the circuit, and a priority encoder that allows spiking neurons to sequentially access the synapse array.
    Type: Grant
    Filed: June 14, 2016
    Date of Patent: April 21, 2020
    Assignee: International Business Machines Corporation
    Inventors: Bernard V. Brezzo, Leland Chang, Steven K. Esser, Daniel J. Friedman, Yong Liu, Dharmendra S. Modha, Robert K. Montoye, Bipin Rajendran, Jae-sun Seo, Jose A. Tierno
  • Patent number: 10579092
    Abstract: Aspects include a method for generating a signal in response to an event. The method includes receiving, from a clock signal generator, a clock signal, wherein the clock signal has a fixed clock period. The method further includes receiving an indication of a pulse and, responsive to receiving the indication of the pulse, generating an output comprising a high voltage having a starting time and an ending time. The starting time is a first time when the indication of the asynchronous event is received, and the ending time is a second time at one fixed clocked period from the starting time.
    Type: Grant
    Filed: November 1, 2016
    Date of Patent: March 3, 2020
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Daniel J. Friedman, Seongwon Kim, Bipin Rajendran
  • Publication number: 20180232005
    Abstract: Aspects include a method for generating a signal in response to an event. The method includes receiving, from a clock signal generator, a clock signal, wherein the clock signal has a fixed clock period. The method further includes receiving an indication of a pulse and, responsive to receiving the indication of the pulse, generating an output comprising a high voltage having a starting time and an ending time. The starting time is a first time when the indication of the asynchronous event is received, and the ending time is a second time at one fixed clocked period from the starting time.
    Type: Application
    Filed: November 1, 2016
    Publication date: August 16, 2018
    Inventors: DANIEL J. FRIEDMAN, SEONGWON KIM, BIPIN RAJENDRAN
  • Publication number: 20180197073
    Abstract: One embodiment relates to a neuromorphic network including electronic neurons and an interconnect circuit for interconnecting the neurons. The interconnect circuit includes synaptic devices for interconnecting the neurons via axon paths, dendrite paths and membrane paths. Each synaptic device includes a variable state resistor and a transistor device with a gate terminal, a source terminal and a drain terminal, wherein the drain terminal is connected in series with a first terminal of the variable state resistor. The source terminal of the transistor device is connected to an axon path, the gate terminal of the transistor device is connected to a membrane path and a second terminal of the variable state resistor is connected to a dendrite path, such that each synaptic device is coupled between a first axon path and a first dendrite path, and between a first membrane path and said first dendrite path.
    Type: Application
    Filed: March 9, 2018
    Publication date: July 12, 2018
    Inventors: Daniel J. Friedman, Seongwon Kim, Chung H. Lam, Dharmendra S. Modha, Bipin Rajendran, Jose A. Tierno
  • Publication number: 20180197074
    Abstract: One embodiment relates to a neuromorphic network including electronic neurons and an interconnect circuit for interconnecting the neurons. The interconnect circuit includes synaptic devices for interconnecting the neurons via axon paths, dendrite paths and membrane paths. Each synaptic device includes a variable state resistor and a transistor device with a gate terminal, a source terminal and a drain terminal, wherein the drain terminal is connected in series with a first terminal of the variable state resistor. The source terminal of the transistor device is connected to an axon path, the gate terminal of the transistor device is connected to a membrane path and a second terminal of the variable state resistor is connected to a dendrite path, such that each synaptic device is coupled between a first axon path and a first dendrite path, and between a first membrane path and said first dendrite path.
    Type: Application
    Filed: March 9, 2018
    Publication date: July 12, 2018
    Inventors: Daniel J. Friedman, Seongwon Kim, Chung H. Lam, Dharmendra S. Modha, Bipin Rajendran, Jose A. Tierno
  • Patent number: 9953261
    Abstract: Embodiments of the invention relate to a neuromorphic network for producing spike-timing dependent plasticity. The neuromorphic network includes a plurality of electronic neurons and an interconnect circuit coupled for interconnecting the plurality of electronic neurons. The interconnect circuit includes plural synaptic devices for interconnecting the electronic neurons via axon paths, dendrite paths and membrane paths. Each synaptic device includes a variable state resistor and a transistor device with a gate terminal, a source terminal and a drain terminal, wherein the drain terminal is connected in series with a first terminal of the variable state resistor.
    Type: Grant
    Filed: January 7, 2016
    Date of Patent: April 24, 2018
    Assignee: International Business Machines Corporation
    Inventors: Daniel J. Friedman, Seongwon Kim, Chung H. Lam, Dharmendra S. Modha, Bipin Rajendran, Jose A. Tierno
  • Patent number: 9946969
    Abstract: Embodiments of the invention relate to a neuromorphic network for producing spike-timing dependent plasticity. The neuromorphic network includes a plurality of electronic neurons and an interconnect circuit coupled for interconnecting the plurality of electronic neurons. The interconnect circuit includes plural synaptic devices for interconnecting the electronic neurons via axon paths, dendrite paths and membrane paths. Each synaptic device includes a variable state resistor and a transistor device with a gate terminal, a source terminal and a drain terminal, wherein the drain terminal is connected in series with a first terminal of the variable state resistor.
    Type: Grant
    Filed: January 7, 2016
    Date of Patent: April 17, 2018
    Assignee: International Business Machines Corporation
    Inventors: Daniel J. Friedman, Seongwon Kim, Chung H. Lam, Dharmendra S. Modha, Bipin Rajendran, Jose A. Tierno
  • Publication number: 20160358067
    Abstract: A reconfigurable neural network circuit is provided. The reconfigurable neural network circuit comprises an electronic synapse array including multiple synapses interconnecting a plurality of digital electronic neurons. Each neuron comprises an integrator that integrates input spikes and generates a signal when the integrated inputs exceed a threshold. The circuit further comprises a control module for reconfiguring the synapse array. The control module comprises a global final state machine that controls timing for operation of the circuit, and a priority encoder that allows spiking neurons to sequentially access the synapse array.
    Type: Application
    Filed: August 22, 2016
    Publication date: December 8, 2016
    Inventors: Bernard V. Brezzo, Leland Chang, Steven K. Esser, Daniel J. Friedman, Yong Liu, Dharmendra S. Modha, Robert K. Montoye, Bipin Rajendran, Jae-sun Seo, Jose A. Tierno
  • Publication number: 20160292569
    Abstract: A reconfigurable neural network circuit is provided. The reconfigurable neural network circuit comprises an electronic synapse array including multiple synapses interconnecting a plurality of digital electronic neurons. Each neuron comprises an integrator that integrates input spikes and generates a signal when the integrated inputs exceed a threshold. The circuit further comprises a control module for reconfiguring the synapse array. The control module comprises a global final state machine that controls timing for operation of the circuit, and a priority encoder that allows spiking neurons to sequentially access the synapse array.
    Type: Application
    Filed: June 14, 2016
    Publication date: October 6, 2016
    Inventors: Bernard V. Brezzo, Leland Chang, Steven K. Esser, Daniel J. Friedman, Yong Liu, Dharmendra S. Modha, Robert K. Montoye, Bipin Rajendran, Jae-sun Seo, Jose A. Tierno
  • Patent number: 9460383
    Abstract: A reconfigurable neural network circuit is provided. The reconfigurable neural network circuit comprises an electronic synapse array including multiple synapses interconnecting a plurality of digital electronic neurons. Each neuron comprises an integrator that integrates input spikes and generates a signal when the integrated inputs exceed a threshold. The circuit further comprises a control module for reconfiguring the synapse array. The control module comprises a global final state machine that controls timing for operation of the circuit, and a priority encoder that allows spiking neurons to sequentially access the synapse array.
    Type: Grant
    Filed: September 2, 2014
    Date of Patent: October 4, 2016
    Assignee: International Business Machines Corporation
    Inventors: Bernard V. Brezzo, Leland Chang, Steven K. Esser, Daniel J. Friedman, Yong Liu, Dharmendra S. Modha, Robert K. Montoye, Bipin Rajendran, Jae-sun Seo, Jose A. Tierno
  • Publication number: 20160247063
    Abstract: A reconfigurable neural network circuit is provided. The reconfigurable neural network circuit comprises an electronic synapse array including multiple synapses interconnecting a plurality of digital electronic neurons. Each neuron comprises an integrator that integrates input spikes and generates a signal when the integrated inputs exceed a threshold. The circuit further comprises a control module for reconfiguring the synapse array. The control module comprises a global final state machine that controls timing for operation of the circuit, and a priority encoder that allows spiking neurons to sequentially access the synapse array.
    Type: Application
    Filed: September 2, 2014
    Publication date: August 25, 2016
    Inventors: Bernard V. Brezzo, Leland Chang, Steven K. Esser, Daniel J. Friedman, Yong Liu, Dharmendra S. Modha, Robert K. Montoye, Bipin Rajendran, Jae-Sun Seo, Jose A. Tierno
  • Publication number: 20160224890
    Abstract: Embodiments of the invention relate to a neuromorphic network for producing spike-timing dependent plasticity. The neuromorphic network includes a plurality of electronic neurons and an interconnect circuit coupled for interconnecting the plurality of electronic neurons. The interconnect circuit includes plural synaptic devices for interconnecting the electronic neurons via axon paths, dendrite paths and membrane paths. Each synaptic device includes a variable state resistor and a transistor device with a gate terminal, a source terminal and a drain terminal, wherein the drain terminal is connected in series with a first terminal of the variable state resistor.
    Type: Application
    Filed: January 7, 2016
    Publication date: August 4, 2016
    Inventors: Daniel J. Friedman, Seongwon Kim, Chung H. Lam, Dharmendra S. Modha, Bipin Rajendran, Jose A. Tierno
  • Publication number: 20160224887
    Abstract: Embodiments of the invention relate to a neuromorphic network for producing spike-timing dependent plasticity. The neuromorphic network includes a plurality of electronic neurons and an interconnect circuit coupled for interconnecting the plurality of electronic neurons. The interconnect circuit includes plural synaptic devices for interconnecting the electronic neurons via axon paths, dendrite paths and membrane paths. Each synaptic device includes a variable state resistor and a transistor device with a gate terminal, a source terminal and a drain terminal, wherein the drain terminal is connected in series with a first terminal of the variable state resistor.
    Type: Application
    Filed: January 7, 2016
    Publication date: August 4, 2016
    Inventors: Daniel J. Friedman, Seongwon Kim, Chung H. Lam, Dharmendra S. Modha, Bipin Rajendran, Jose A. Tierno
  • Patent number: 9269042
    Abstract: Embodiments of the invention relate to a neuromorphic network for producing spike-timing dependent plasticity. The neuromorphic network includes a plurality of electronic neurons and an interconnect circuit coupled for interconnecting the plurality of electronic neurons. The interconnect circuit includes plural synaptic devices for interconnecting the electronic neurons via axon paths, dendrite paths and membrane paths. Each synaptic device includes a variable state resistor and a transistor device with a gate terminal, a source terminal and a drain terminal, wherein the drain terminal is connected in series with a first terminal of the variable state resistor.
    Type: Grant
    Filed: September 30, 2010
    Date of Patent: February 23, 2016
    Assignee: International Business Machines Corporation
    Inventors: Daniel J. Friedman, Seongwon Kim, Chung H. Lam, Dharmendra S. Modha, Bipin Rajendran, Jose A. Tierno
  • Patent number: 9159920
    Abstract: An example embodiment disclosed is a process for fabricating a phase change memory cell. The method includes forming a bottom electrode, creating a pore in an insulating layer above the bottom electrode, depositing piezoelectric material in the pore, depositing phase change material in the pore proximate the piezoelectric material, and forming a top electrode over the phase change material. Depositing the piezoelectric material in the pore may include conforming the piezoelectric material to at least one wall defining the pore such that the piezoelectric material is deposited between the phase change material and the wall. The conformal deposition may be achieved by chemical vapor deposition (CVD) or by atomic layer deposition (ALD).
    Type: Grant
    Filed: July 24, 2013
    Date of Patent: October 13, 2015
    Assignee: International Business Machines Corporation
    Inventors: Catherine A. Dubourdieu, Martin M. Frank, Bipin Rajendran, Alejandro G. Schrott
  • Patent number: 9064794
    Abstract: An integrated circuit includes a substrate including isolation regions, a first conductive line formed in the substrate between isolation regions, and a vertical diode formed in the substrate. The integrated circuit includes a contact coupled to the vertical diode and a memory element coupled to the contact. The first conductive line provides a portion of the vertical diode.
    Type: Grant
    Filed: November 7, 2013
    Date of Patent: June 23, 2015
    Assignees: International Business Machines Corporation, Macronix International Co., Ltd, Qimonda AG
    Inventors: Thomas Happ, Hsiang-Lan Lung, Bipin Rajendran, Min Yang
  • Patent number: 9047938
    Abstract: A three dimensional (3D) stack of phase change memory (PCM) devices which includes PCM devices stacked in a 3D array, the PCM devices having memory regions; a memory management unit on at least one of the PCM devices; a stack controller in the memory management unit to monitor an ambient device temperature (Tambient) with respect to a neighborhood of memory regions in the PCM devices and to adjust a programming current with respect to at least one of the memory regions in the neighborhood of memory regions in accordance with the Tambient. Also disclosed is a method of programming a PCM device.
    Type: Grant
    Filed: February 25, 2013
    Date of Patent: June 2, 2015
  • Patent number: 8933536
    Abstract: Memory cells having memory elements self-aligned with the emitters of bipolar junction transistor access devices are described herein, as well as methods for manufacturing such devices. A memory device as described herein comprises a plurality of memory cells. Memory cells in the plurality of memory cells include a bipolar junction transistor comprising an emitter comprising a pillar of doped polysilicon. The memory cells include an insulating element over the emitter and having an opening extending through the insulating layer, the opening centered over the emitter. The memory cells also include a memory element within the opening and electrically coupled to the emitter.
    Type: Grant
    Filed: January 22, 2009
    Date of Patent: January 13, 2015
    Assignees: Macronix International Co., Ltd., International Business Machines Corporation
    Inventors: Hsiang-Lan Lung, Erh-Kun Lai, Chung H. Lam, Bipin Rajendran
  • Patent number: 8898097
    Abstract: A reconfigurable neural network circuit is provided. The reconfigurable neural network circuit comprises an electronic synapse array including multiple synapses interconnecting a plurality of digital electronic neurons. Each neuron comprises an integrator that integrates input spikes and generates a signal when the integrated inputs exceed a threshold. The circuit further comprises a control module for reconfiguring the synapse array. The control module comprises a global final state machine that controls timing for operation of the circuit, and a priority encoder that allows spiking neurons to sequentially access the synapse array.
    Type: Grant
    Filed: August 16, 2012
    Date of Patent: November 25, 2014
    Assignee: International Business Machines Corporation
    Inventors: Bernard V. Brezzo, Leland Chang, Steven K. Esser, Daniel J. Friedman, Yong Liu, Dharmendra S. Modha, Robert K. Montoye, Bipin Rajendran, Jae-sun Seo, Jose A. Tierno