Avijit Chakraborty

US Patent:

20170032247, Feb 2, 2017

Filed:

Sep 18, 2015

Appl. No.:

14/859082

Inventors:

- San Diego CA, US
Avijit CHAKRABORTY - San Diego CA, US
David Jonathan JULIAN - San Diego CA, US
Henricus Meinardus STOKMAN - Amsterdam, NL
Ork DE ROOIJ - Utrecht, NL
Koen Erik Adriaan VAN DE SANDE - Breukelen, NL
Venkata Sreekanta Reddy ANNAPUREDDY - San Diego CA, US

International Classification:

G06N 3/08
G06N 3/04
G06N 99/00

Abstract:

Multi-label classification is improved by determining thresholds and/or scale factors. Selecting thresholds for multi-label classification includes sorting a set of label scores associated with a first label to create an ordered list. Precision and recall values are calculated corresponding to a set of candidate thresholds from score values. The threshold is selected from the candidate thresholds for the first label based on target precision values or recall values. A scale factor is also selected for an activation function for multi-label classification where a metric of scores within a range is calculated. The scale factor is adjusted when the metric of scores are not within the range.

US Patent:

20150278683, Oct 1, 2015

Filed:

Mar 27, 2014

Appl. No.:

14/228078

Inventors:

- San Diego CA, US
Sarah Paige GIBSON - San Diego CA, US
Jeffrey Alexander LEVIN - San Diego CA, US
Ravindra Manohar PATWARDHAN - San Diego CA, US
Avijit CHAKRABORTY - San Diego CA, US
William Howard CONSTABLE - San Diego CA, US

Assignee:

QUALCOMM Incorporated - San Diego CA

International Classification:

G06N 3/08
G06N 3/04

Abstract:

A method for managing synapse plasticity in a neural network includes converting a first set of synapses from a plastic synapse type to a fixed synapse type. The method may also include converting a second set of synapses from the fixed synapse type to the plastic synapse type.

US Patent:

20150100531, Apr 9, 2015

Filed:

Mar 25, 2014

Appl. No.:

14/224997

Inventors:

- San Diego CA, US
Tejash Rajnikant SHAH - San Diego CA, US
Jesse Shoresh HOSE - Carlsbad CA, US
Avijit CHAKRABORTY - San Diego CA, US
Ramakrishna KINTADA - San Diego CA, US

Assignee:

QUALCOMM Incorporated - San Diego CA

International Classification:

G06N 3/02
G05B 15/02

US Classification:

706 25, 706 15

Abstract:

Aspects of the present disclosure provide methods and apparatus for remotely controlling and monitoring neural model execution (e.g., such as execution of the neural models described above) remotely, such as via the Internet. According to certain aspects, a client at a remote location (e.g., a webclient), may establish a connection with a server on which the neural model is running (or at least capable of controlling and monitoring the execution).