Search

Csaba Petre

from San Diego, CA
Age ~39
Get Report
Also known as:
Petra Csaba
Related to:
Ibolya N Szuromi, 64Peter Petre, 63
Connected to:
Catrinel Petre, 35Christopher D Petre, 49Craig M Petre, 39Cristian Petre, 55Dewayna A Petre, 56Edward C Petre, 75Gabriel PetreGina M Petre, 52James E Petre, 67Jean E Petre, 98

Csaba Petre Phones & Addresses

  • San Diego, CA
  • Oak Park, CA
  • Cardiff by the Sea, CA
  • Kenai, AK

Resumes

Resumes

Csaba Petre Photo 1

Senior Scientist, Science Team Lead

View page
Location:
San Diego, CA
Industry:
Consumer Services
Work:
Cleverpet Oct 2016 - Feb 2018
Software Engineer
Accel Robotics Oct 2016 - Feb 2018
Senior Scientist, Science Team Lead
Brain Corp Oct 2009 - Oct 2016
Scientist
Education:
Georgia Institute of Technology 2007 - 2009
Masters, Electrical Engineering University of California, Los Angeles 2003 - 2007
Bachelors, Electrical Engineering
Skills:
Machine Learning
Python
Artificial Intelligence
C++
Computer Science
Computer Vision
Programming
Algorithms
Science
Software Engineering
Matlab
Java
Data Analysis
Software Development
Csaba Petre Photo 2

Csaba Petre

View page

Publications

Us Patents

Systems And Methods For Invariant Pulse Latency Coding

View page
US Patent:
8315305, Nov 20, 2012
Filed:
Aug 26, 2010
Appl. No.:
12/869573
Inventors:
Csaba Petre - San Diego CA, US
Botond Szatmary - San Diego CA, US
Eugene M. Izhikevich - San Diego CA, US
Assignee:
Brain Corporation - San Diego CA
International Classification:
H04N 11/02
US Classification:
37524001, 37524025, 37524026
Abstract:
Image processing systems and methods extract information from an input signal representative of an element of an image and to encode the information in a pulsed output signal. A plurality of channels communicates the pulsed output signal, each of the plurality of channels being characterized by a latency. The information may be encoded as a pattern of relative pulse latencies observable in pulses communicated through the plurality of channels and the pattern of relative pulse latencies is substantially insensitive to image contrast and/or image luminance. A filter can be employed to provide a generator signal based on the input signal and pulse latencies can be determined using a logarithmic function of the generator signal. The filter may be temporally and/or spatially balanced and characterized by an integral along spatial and/or temporal dimensions of the filter that is substantially zero for all values of a temporal and/or a spatial variable.

Invariant Pulse Latency Coding Systems And Methods Systems And Methods

View page
US Patent:
8467623, Jun 18, 2013
Filed:
Aug 26, 2010
Appl. No.:
12/869583
Inventors:
Eugene M. Izhikevich - San Diego CA, US
Botond Szatmary - San Diego CA, US
Csaba Petre - San Diego CA, US
Assignee:
Brain Corporation - San Diego CA
International Classification:
G06F 17/00
G06K 9/36
G06K 9/46
G06K 9/32
G06K 9/40
H03K 7/04
H03K 9/04
H03K 7/06
H03K 9/06
H04B 14/04
H04N 7/24
G06F 15/18
G06J 1/00
G06N 3/00
A61N 1/00
US Classification:
382239, 382254, 382298, 375239, 706 35, 708101, 348471, 607141
Abstract:
Systems and methods for processing image signals are described. One method comprises obtaining a generator signal based on an image signal and determining relative latencies associated with two or more pulses in a pulsed signal using a function of the generator signal that can comprise a logarithmic function. The function of the generator signal can be the absolute value of its argument. Information can be encoded in the pattern of relative latencies. Latencies can be determined using a scaling parameter that is calculated from a history of the image signal. The pulsed signal is typically received from a plurality of channels and the scaling parameter corresponds to at least one of the channels. The scaling parameter may be adaptively calculated such that the latency of the next pulse falls within one or more of a desired interval and an optimal interval.

Apparatus And Methods For Temporally Proximate Object Recognition

View page
US Patent:
20120308076, Dec 6, 2012
Filed:
Jun 2, 2011
Appl. No.:
13/152105
Inventors:
Filip Lukasz Piekniewski - San Diego CA, US
Csaba Petre - San Diego CA, US
Sach Hansen Sokol - La Jolla CA, US
Botond Szatmary - San Diego CA, US
Jayram Moorkanikara Nageswaran - San Diego CA, US
Eugene M. Izhikevich - San Diego CA, US
International Classification:
G06K 9/00
US Classification:
382103
Abstract:
Object recognition apparatus and methods useful for extracting information from an input signal. In one embodiment, the input signal is representative of an element of an image, and the extracted information is encoded into patterns of pulses. The patterns of pulses are directed via transmission channels to a plurality of detector nodes configured to generate an output pulse upon detecting an object of interest. Upon detecting a particular object, a given detector node elevates its sensitivity to that particular object when processing subsequent inputs. In one implementation, one or more of the detector nodes are also configured to prevent adjacent detector nodes from generating detection signals in response to the same object representation. The object recognition apparatus modulates properties of the transmission channels by promoting contributions from channels carrying information used in object recognition.

Elementary Network Description For Efficient Memory Management In Neuromorphic Systems

View page
US Patent:
20130073484, Mar 21, 2013
Filed:
Sep 21, 2011
Appl. No.:
13/239155
Inventors:
Eugene M. Izhikevich - San Diego CA, US
Botond Szatmary - San Diego CA, US
Csaba Petre - San Diego CA, US
Filip Piekniewski - San Diego CA, US
International Classification:
G06N 3/04
US Classification:
706 10, 706 27
Abstract:
A simple format is disclosed and referred to as Elementary Network Description (END). The format can fully describe a large-scale neuronal model and embodiments of software or hardware engines to simulate such a model efficiently. The architecture of such neuromorphic engines is optimal for high-performance parallel processing of spiking networks with spike-timing dependent plasticity. Methods for managing memory in a processing system are described whereby memory can be allocated among a plurality of elements and rules configured for each element such that the parallel execution of the spiking networks is most optimal.

Elementary Network Description For Efficient Implementation Of Event-Triggered Plasticity Rules In Neuromorphic Systems

View page
US Patent:
20130073492, Mar 21, 2013
Filed:
Sep 21, 2011
Appl. No.:
13/239163
Inventors:
Eugene M. Izhikevich - San Diego CA, US
Botond Szatmary - San Diego CA, US
Csaba Petre - San Diego CA, US
Filip Piekniewski - San Diego CA, US
Jayram Moorkanikara Nageswaran - San Diego CA, US
International Classification:
G05B 13/02
US Classification:
706 23
Abstract:
A simple format is disclosed and referred to as Elementary Network Description (END). The format can fully describe a large-scale neuronal model and embodiments of software or hardware engines to simulate such a model efficiently. The architecture of such neuromorphic engines is optimal for high-performance parallel processing of spiking networks with spike-timing dependent plasticity. The software and hardware engines are optimized to take into account short-term and long-term synaptic plasticity in the form of LTD, LTP, and STDP.

Elementary Network Description For Neuromorphic Systems

View page
US Patent:
20130073495, Mar 21, 2013
Filed:
Sep 21, 2011
Appl. No.:
13/239123
Inventors:
Eugene M. Izhikevich - San Diego CA, US
Botond Szatmary - San Diego CA, US
Csaba Petre - San Diego CA, US
Jayram Moorkanikara Nageswaran - San Diego CA, US
Filip Piekniewski - San Diego CA, US
International Classification:
G06N 3/08
G06N 3/04
US Classification:
706 25, 706 27
Abstract:
A simple format is disclosed and referred to as Elementary Network Description (END). The format can fully describe a large-scale neuronal model and embodiments of software or hardware engines to simulate such a model efficiently. The architecture of such neuromorphic engines is optimal for high-performance parallel processing of spiking networks with spike-timing dependent plasticity. Neuronal network and methods for operating neuronal networks comprise a plurality of units, where each unit has a memory and a plurality of doublets, each doublet being connected to a pair of the plurality of units. Execution of unit update rules for the plurality of units is order-independent and execution of doublet event rules for the plurality of doublets is order-independent.

Elementary Network Description For Efficient Link Between Neuronal Models And Neuromorphic Systems

View page
US Patent:
20130073498, Mar 21, 2013
Filed:
Sep 21, 2011
Appl. No.:
13/239148
Inventors:
Eugene M. Izhikevich - San Diego CA, US
Csaba Petre - San Diego CA, US
Filip Piekniewski - San Diego CA, US
Botond Szatmary - San Diego CA, US
International Classification:
G06N 3/04
US Classification:
706 27, 706 15
Abstract:
A simple format is disclosed and referred to as Elementary Network Description (END). The format can fully describe a large-scale neuronal model and embodiments of software or hardware engines to simulate such a model efficiently. The architecture of such neuromorphic engines is optimal for high-performance parallel processing of spiking networks with spike-timing dependent plasticity. The format is specifically tuned for neural systems and specialized neuromorphic hardware, thereby serving as a bridge between developers of brain models and neuromorphic hardware manufactures.

Invariant Pulse Latency Coding Systems And Methods

View page
US Patent:
20130251278, Sep 26, 2013
Filed:
May 15, 2013
Appl. No.:
13/895246
Inventors:
Eugene M. Izhikevich - San Diego CA, US
Botond Szatmary - San Diego CA, US
Csaba Petre - San Diego CA, US
International Classification:
G06T 9/00
US Classification:
382236
Abstract:
Systems and methods for processing image signals are described. One method comprises obtaining a generator signal based on an image signal and determining relative latencies associated with two or more pulses in a pulsed signal using a function of the generator signal that can comprise a logarithmic function. The function of the generator signal can be the absolute value of its argument. Information can be encoded in the pattern of relative latencies. Latencies can be determined using a scaling parameter that is calculated from a history of the image signal. The pulsed signal is typically received from a plurality of channels and the scaling parameter corresponds to at least one of the channels. The scaling parameter may be adaptively calculated such that the latency of the next pulse falls within one or more of a desired interval and an optimal interval.
Control profile
Csaba Petre from San Diego, CA, age ~39 Get Report