{"id":"W119215678","doi":"10.1007/978-3-642-30353-1_17","title":"Image Morphing: Transfer Learning between Tasks That Have Multiple Outputs","year":2012,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Acadia University","funders":"","keywords":"Computer science; Transfer of learning; Morphing; Artificial intelligence; Task (project management); Artificial neural network; Machine learning; Context (archaeology); Multiplicative function; Multi-task learning; Transformation (genetics); Domain (mathematical analysis); Image (mathematics); Inductive transfer; Pattern recognition (psychology); 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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001695059,0.0007673871,0.0007578988,0.0009833046,0.0006031661,0.001055197,0.003228947,0.0004742808,0.00007416664],"category_scores_gemma":[0.0001796859,0.0007368166,0.0002609746,0.0004491515,0.0005848971,0.001550256,0.0009875334,0.002186638,0.0002158722],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002841002,"about_ca_system_score_gemma":0.0002999498,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003475854,"about_ca_topic_score_gemma":0.000030913,"domain_scores_codex":[0.9947876,0.0001240465,0.0006331516,0.001739288,0.001504,0.001211907],"domain_scores_gemma":[0.9968222,0.001064752,0.0002646732,0.001193313,0.0002193609,0.0004356994],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008310441,0.00003406412,0.004619219,0.00005868075,0.00003467875,0.00009907453,0.006684495,0.02317275,0.0008318926,0.006195734,0.00001615319,0.9582449],"study_design_scores_gemma":[0.001652429,0.0003528942,0.006248289,0.0007821271,0.00005859368,0.0001303051,0.000006132733,0.9131293,0.004994852,0.02358184,0.04594483,0.003118421],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.000366413,0.0005955313,0.9915138,0.000642025,0.001111972,0.0004174441,0.000004801592,0.0003872383,0.004960753],"genre_scores_gemma":[0.697387,0.00004234806,0.3002252,0.00076204,0.0007011652,0.000009299191,0.00001639626,0.00007067154,0.0007858796],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9551265,"threshold_uncertainty_score":0.9999818,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03987737130813371,"score_gpt":0.257223916041184,"score_spread":0.2173465447330503,"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."}}