{"id":"W2276570126","doi":"10.1371/journal.pone.0149928","title":"Optimizing Semantic Pointer Representations for Symbol-Like Processing in Spiking Neural Networks","year":2016,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Advanced Memory and Neural Computing","field":"Engineering","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Compute Canada","keywords":"Computer science; Pointer (user interface); Artificial neural network; Computation; Artificial intelligence; Heuristic; Transformation (genetics); Neuromorphic engineering; Latency (audio); Theoretical computer science; Algorithm","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007501493,0.0001128329,0.0001656744,0.00007353917,0.00007449188,0.00003313853,0.00008816846,0.00003764976,0.000006749408],"category_scores_gemma":[0.00005023062,0.0000962383,0.0000357551,0.0001304574,0.00001510938,0.0003767858,0.0000317298,0.0001167091,0.000002348667],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000387873,"about_ca_system_score_gemma":0.000003284005,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":6.451988e-7,"about_ca_topic_score_gemma":0.000005773898,"domain_scores_codex":[0.999207,0.00001220432,0.0002173128,0.0001847339,0.00007904323,0.0002996723],"domain_scores_gemma":[0.9996486,0.0001244951,0.00003429543,0.0001232143,0.00002900654,0.00004038887],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005970709,0.0001597353,0.003345871,0.000575445,0.00005374217,0.00002646511,0.0008133594,0.613872,0.3496238,0.00004223186,0.00003172544,0.03139596],"study_design_scores_gemma":[0.0006405303,0.00002479463,0.0004949086,0.0009821632,0.00002720868,0.000003912707,0.00007849342,0.9582714,0.03913384,0.0001478977,0.000004600524,0.0001902776],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7959697,0.0002486446,0.2029325,0.0001091344,0.00009807853,0.0002461968,9.093594e-7,0.0002463158,0.0001485096],"genre_scores_gemma":[0.9917613,0.00001609641,0.007824415,0.00005623788,0.0001880216,0.00003696908,0.000001946898,0.00003829201,0.00007678231],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3443994,"threshold_uncertainty_score":0.3924484,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04410978073342397,"score_gpt":0.253967972887517,"score_spread":0.209858192154093,"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."}}