{"id":"W4389042697","doi":"10.1016/j.patrec.2023.11.026","title":"Basis scaling and double pruning for efficient inference in network-based transfer learning","year":2023,"lang":"en","type":"article","venue":"Pattern Recognition Letters","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University","funders":"","keywords":"Pruning; Computer science; MNIST database; Basis (linear algebra); Inference; Artificial intelligence; Reduction (mathematics); Transfer of learning; Deep learning; Algorithm; Pattern recognition (psychology); Machine learning; Mathematics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007564212,0.0001395257,0.0001512195,0.0002816005,0.0002131801,0.0002096705,0.000167144,0.00005017105,0.00001908663],"category_scores_gemma":[0.00006454541,0.0001539099,0.00005536265,0.0005965055,0.00003075167,0.0001892457,0.00004063214,0.0002229467,0.00005220158],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003220763,"about_ca_system_score_gemma":0.00002077191,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002516221,"about_ca_topic_score_gemma":0.00001395804,"domain_scores_codex":[0.998621,0.0001153389,0.0002612844,0.0003985184,0.0001914058,0.0004123985],"domain_scores_gemma":[0.9991092,0.0006060519,0.00005250776,0.0001125083,0.00004411352,0.00007562065],"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":[0.00002977251,0.00002029051,0.01598972,0.00007402391,0.000009993033,0.00001451272,0.001811013,0.630521,0.001607282,0.00006238669,0.00005475919,0.3498053],"study_design_scores_gemma":[0.001747224,0.00003431757,0.01025066,0.0002042073,0.000006310587,0.000001420683,0.0001109623,0.9862049,0.0006050523,0.00006582398,0.0005229834,0.0002461342],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4167143,0.000007784646,0.581179,0.001568218,0.0001239034,0.0001941264,0.000001414867,0.0001721656,0.00003904936],"genre_scores_gemma":[0.9901593,0.000007085926,0.006764839,0.002804137,0.00006338026,0.0001220213,0.00004960268,0.00001816495,0.00001147552],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5744142,"threshold_uncertainty_score":0.6276263,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04860436396260664,"score_gpt":0.2698073820698968,"score_spread":0.2212030181072902,"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."}}