Shihao Ji Phones & Addresses
-
Marietta, GA
-
Portland, OR
-
Bellevue, WA
-
Hillsboro, OR
-
Durham, NC
-
Brooklyn, NY
-
Kiona, WA
-
Santa Clara, CA
-
1315 Morreene Rd APT 8G, Durham, NC 27705
Work
Position:
Administrative Support Occupations, Including Clerical Occupations
Publications
Us Patents
Multiplication-Free Approximation For Neural Networks And Sparse Coding
View pageUS Patent:
20210027029, Jan 28, 2021
Filed:
Oct 12, 2020
Appl. No.:
17/067979
Inventors:
- Santa Clara CA, US
Shihao Ji - Portland OR, US
Arnab Paul - Hillsboro OR, US
Shihao Ji - Portland OR, US
Arnab Paul - Hillsboro OR, US
Assignee:
Intel Corporation - Santa Clara CA
International Classification:
G06K 7/10
G06N 20/10
G06F 7/487
G06F 7/483
G06N 3/04
G06F 17/16
G06K 7/14
G06N 20/10
G06F 7/487
G06F 7/483
G06N 3/04
G06F 17/16
G06K 7/14
Abstract:
Systems, apparatuses and methods may provide for replacing floating point matrix multiplication operations with an approximation algorithm or computation in applications that involve sparse codes and neural networks. The system may replace floating point matrix multiplication operations in sparse code applications and neural network applications with an approximation computation that applies an equivalent number of addition and/or subtraction operations.
Multiplication-Free Approximation For Neural Networks And Sparse Coding
View pageUS Patent:
20190130148, May 2, 2019
Filed:
Jun 29, 2016
Appl. No.:
16/306736
Inventors:
- Santa Clara CA, US
Shihao Ji - Hillsboro OR, US
Arnab Paul - Hillsboro OR, US
Shihao Ji - Hillsboro OR, US
Arnab Paul - Hillsboro OR, US
International Classification:
G06K 7/10
G06F 17/16
G06N 20/10
G06N 3/04
G06K 7/14
G06F 17/16
G06N 20/10
G06N 3/04
G06K 7/14
Abstract:
Systems, apparatuses and methods may provide for replacing floating point matrix multiplication operations with an approximation algorithm or computation in applications that involve sparse codes and neural networks. The system may replace floating point matrix multiplication operations in sparse code applications and neural network applications with an approximation computation that applies an equivalent number of addition and/or subtraction operations.
Performing Power Management In A Multicore Processor
View pageUS Patent:
20160239065, Aug 18, 2016
Filed:
Feb 13, 2015
Appl. No.:
14/621731
Inventors:
VICTOR W. LEE - SANTA CLARA CA, US
DAEHYUN KIM - SAN JOSE CA, US
YUXIN BAI - SAN JOSE CA, US
SHIHAO JI - PORTLAND OR, US
SHENG LI - SANTA CLARA CA, US
DHIRAJ D. KALAMKAR - BANGALORE, IN
NAVEEN K. MELLEMPUDI - BANGALORE, IN
DAEHYUN KIM - SAN JOSE CA, US
YUXIN BAI - SAN JOSE CA, US
SHIHAO JI - PORTLAND OR, US
SHENG LI - SANTA CLARA CA, US
DHIRAJ D. KALAMKAR - BANGALORE, IN
NAVEEN K. MELLEMPUDI - BANGALORE, IN
International Classification:
G06F 1/32
G06F 9/50
G06F 9/50
Abstract:
In an embodiment, a processor a plurality of cores to independently execute instructions, the cores including a plurality of counters to store performance information, and a power controller coupled to the plurality of cores, the power controller having a logic to receive performance information from at least some of the plurality of counters, determine a number of cores to be active and a performance state for the number of cores for a next operation interval, based at least in part on the performance information and model information, and cause the number of cores to be active during the next operation interval, the performance information associated with execution of a workload on one or more of the plurality of cores. Other embodiments are described and claimed.
Query Simplification
View pageUS Patent:
20140279995, Sep 18, 2014
Filed:
Mar 14, 2013
Appl. No.:
13/828948
Inventors:
- Redmond WA, US
Xiaodong He - Issaquah WA, US
Xiaolong Li - Redmond WA, US
Shihao Ji - Bellevue WA, US
Bin Zhang - Seattle WA, US
Xiaodong He - Issaquah WA, US
Xiaolong Li - Redmond WA, US
Shihao Ji - Bellevue WA, US
Bin Zhang - Seattle WA, US
Assignee:
MICROSOFT CORPORATION - REDMOMD WA
International Classification:
G06F 17/30
US Classification:
707706
Abstract:
Methods, systems, and computer-readable media for query simplification are provided. A search engine executed by a server receives a query. In response, the search engine determines whether the query is a long or hard query. For long or hard queries, the search engine drops one or more terms based on search engine logs. The search engine may utilize statistical models like machine translation, condition random fields, or max entropy, to identify the terms that should be dropped. The search engine obtains search results for the simplified query and transmits the results to a user that provided the query.