[et_pb_section bb_built=”1″][et_pb_row][et_pb_column type=”4_4″][et_pb_text _builder_version=”3.11″]<\/p>\n
Prof. Nikitas J. Dimopoulos<\/a>, University of Victoria, nikitas@ece.uvic.ca<\/a>, 250-721-8902<\/em><\/p>\n [\/et_pb_text][et_pb_text _builder_version=”3.11″]<\/p>\n We have employed quantum annealing techniques to the problem of NN ensemble learning. Quantum annealing can solve very large optimization problems, which require enormous computational time to solve using classical computing methods. Our approach contributed to methodologies developed by 1QBit and utilizing D-Wave’s system represented a purely Canadian solution to the quantum computation effort.<\/p>\n Our methodology includes heuristics that enhance the ability of the trained system to generalize. Our methodology was tested both in simulation using 1 QBit\u2019s environment and through the use of D-Wave\u2019s D-Wave 2X system. QSAR models are of interest in the pharmaceutical industry to assay drug candidates.<\/p>\n 1. Ali Jooya, Babak Keshavarz, Nikitas Dimopoulos and Jaspreet Oberoi \u201cAccelerating Neural Network Ensemble Learning Using Optimization and Quantum Annealing Techniques\u201d 2nd International Workshop on Post Moore’s Era Supercomputing (PMES), Denver, November 13, 2017 doi: 10.1145\/3149526.3149528<\/em><\/p>\n [\/et_pb_text][et_pb_image _builder_version=”3.11″ src=”https:\/\/onlineacademiccommunity.uvic.ca\/matrix\/wp-content\/uploads\/sites\/3543\/2018\/10\/EnsembleNN.png” \/][\/et_pb_column][\/et_pb_row][\/et_pb_section]<\/p>\n","protected":false},"excerpt":{"rendered":" Incorporating Quantum…<\/p>\n","protected":false},"author":6891,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"_et_pb_use_builder":"on","_et_pb_old_content":"","_et_gb_content_width":"","footnotes":""},"class_list":["post-167","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/onlineacademiccommunity.uvic.ca\/matrix\/wp-json\/wp\/v2\/pages\/167","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/onlineacademiccommunity.uvic.ca\/matrix\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/onlineacademiccommunity.uvic.ca\/matrix\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/onlineacademiccommunity.uvic.ca\/matrix\/wp-json\/wp\/v2\/users\/6891"}],"replies":[{"embeddable":true,"href":"https:\/\/onlineacademiccommunity.uvic.ca\/matrix\/wp-json\/wp\/v2\/comments?post=167"}],"version-history":[{"count":6,"href":"https:\/\/onlineacademiccommunity.uvic.ca\/matrix\/wp-json\/wp\/v2\/pages\/167\/revisions"}],"predecessor-version":[{"id":227,"href":"https:\/\/onlineacademiccommunity.uvic.ca\/matrix\/wp-json\/wp\/v2\/pages\/167\/revisions\/227"}],"wp:attachment":[{"href":"https:\/\/onlineacademiccommunity.uvic.ca\/matrix\/wp-json\/wp\/v2\/media?parent=167"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}
\nThe introduction of Quantum Annealing techniques in the NN training pipeline improved the generalization capabilities of the resulting ensembles [1].<\/p>\n
\nWe have used this methodology to develop ensemble NN models that can accurately predict the biological activity of chemical compounds (QSAR), specifically PPAR -\u03b1 and -\u03b3 (peroxisome proliferator activated receptors) agonists among others.<\/p>\n