{"id":"W3049227448","doi":"10.3390/app10165631","title":"Improvement of Heterogeneous Transfer Learning Efficiency by Using Hebbian Learning Principle","year":2020,"lang":"en","type":"article","venue":"Applied Sciences","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Research Foundation of Korea","keywords":"Hebbian theory; Transfer of learning; Leabra; Computer science; Artificial intelligence; Competitive learning; Machine learning; Discriminative model; Unsupervised learning; Multi-task learning; Learning rule; Convolutional neural network; Inductive transfer; Pattern recognition (psychology); Artificial neural network; Task (project management); Robot learning; Wake-sleep algorithm","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006789924,0.0001733104,0.0002263635,0.00008975657,0.0006033274,0.0002006408,0.0009237985,0.00004990335,0.00004486231],"category_scores_gemma":[0.00005800094,0.0001613596,0.00007253692,0.0009660912,0.0002387187,0.0002551472,0.0001870041,0.0002761628,0.0000228699],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002682939,"about_ca_system_score_gemma":0.0001133353,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001690821,"about_ca_topic_score_gemma":0.000001101944,"domain_scores_codex":[0.9978353,0.00006634468,0.0003760489,0.0006214436,0.0006643756,0.0004365334],"domain_scores_gemma":[0.9994037,0.00009056862,0.0001359955,0.0001472544,0.00004314756,0.0001793302],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000009262481,0.00004700689,0.000627132,0.00002705969,0.00001148946,0.000003143026,0.005345508,0.3441155,0.6065166,0.00961568,0.00001005697,0.03367157],"study_design_scores_gemma":[0.00051451,0.0006448724,0.00005888659,0.00001633937,0.000008910598,0.000005520785,0.001189864,0.8576915,0.1305231,0.0001039709,0.00886441,0.0003780541],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4770466,0.00008289419,0.5192863,0.0002195066,0.00006074617,0.0001621464,4.811046e-7,0.0001401735,0.003001054],"genre_scores_gemma":[0.9904954,0.000007989281,0.008952318,0.0004458454,0.00002711951,0.000007323464,0.000001360127,0.00001024195,0.00005240897],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.513576,"threshold_uncertainty_score":0.6580052,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03192544707510132,"score_gpt":0.2608682712757365,"score_spread":0.2289428242006352,"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."}}