{"id":"W2907807896","doi":"10.1109/newcas.2018.8585517","title":"A Multi-Mode Accelerator for Pruned Deep Neural Networks","year":2018,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Convolutional neural network; Computer science; Pruning; Computation; Speedup; Convolutional code; Parallel computing; Memory management; Artificial intelligence; Algorithm; Computer hardware; Semiconductor memory; Decoding methods","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002154675,0.0005000102,0.0003167375,0.0003274872,0.0002676328,0.0004389156,0.001341143,0.0003727251,0.006113732],"category_scores_gemma":[0.0005335176,0.0002597529,0.0002639941,0.0003656638,0.0001359521,0.0006776219,0.0005526374,0.0006596812,0.001251204],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003325567,"about_ca_system_score_gemma":0.0005927942,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009647659,"about_ca_topic_score_gemma":0.002156684,"domain_scores_codex":[0.9998407,0.00001517272,0.00001105918,0.00002970142,0.00007435621,0.00002890656],"domain_scores_gemma":[0.9997846,0.00005114841,0.00002188324,0.0000508236,0.00006850905,0.00002291332],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001907582,0.0003315436,0.003606465,0.0006108407,0.0002187823,0.001136977,0.0003009146,0.05912356,0.2947671,0.01995499,0.03314347,0.5848978],"study_design_scores_gemma":[0.0002031225,0.0007283197,0.002036894,0.00008150686,0.0001054195,0.0007611281,0.00004743772,0.8191356,0.133365,0.007526573,0.03595271,0.00005624313],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.179155,0.001875434,0.7852974,0.0004884075,0.0005158974,0.0001439793,0.000574704,0.01862382,0.01332536],"genre_scores_gemma":[0.6689324,0.0004920607,0.3059637,0.0003919752,0.00007406397,0.000162865,0.0009521922,0.0003972194,0.0226335],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006113732,"threshold_uncertainty_score":0.0204525,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03614531567958412,"score_gpt":0.3190718226373708,"score_spread":0.2829265069577867,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}