{"id":"W2766861616","doi":"10.5687/sss.2017.160","title":"Consecutive Dimensionality Reduction by Canonical Correlation Analysis for Visualization of Convolutional Neural Networks","year":2017,"lang":"en","type":"article","venue":"Proceedings of the ISCIE International Symposium on Stochastic Systems Theory and its Applications","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Japan Society for the Promotion of Science; Canadian Institute for Advanced Research","keywords":"Dimensionality reduction; Visualization; Principal component analysis; Canonical correlation; Pattern recognition (psychology); Computer science; Artificial intelligence; Convolutional neural network; Linear subspace; Subspace topology; Benchmark (surveying); Feature (linguistics); Representation (politics); Artificial neural network; Curse of dimensionality; Data visualization; Feature extraction; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008467348,0.0001255078,0.0002182144,0.0001043507,0.0005699598,0.0001791768,0.0008439567,0.0000747958,0.000003180561],"category_scores_gemma":[0.0003228896,0.0001010348,0.0001118956,0.0002714643,0.0002322213,0.0004352656,0.0002059443,0.00006758672,5.795758e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005451432,"about_ca_system_score_gemma":0.0000344238,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001759283,"about_ca_topic_score_gemma":7.138898e-7,"domain_scores_codex":[0.9986461,0.00003218068,0.0004722027,0.0003453632,0.0003886778,0.0001154404],"domain_scores_gemma":[0.9973366,0.0003299839,0.001034877,0.0002301833,0.001009954,0.00005845214],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005121586,0.00009218464,0.0004450231,0.00002014617,0.0001852263,5.839144e-9,0.00007749364,0.02038018,0.003605533,0.9748572,0.0002231529,0.00006268117],"study_design_scores_gemma":[0.0003569541,0.00005071303,0.001711883,0.00005795707,0.0001769752,0.000005958574,0.00009636861,0.9891334,0.0009274946,0.007092308,0.0002655284,0.0001244396],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01401463,0.00008364959,0.9831704,0.0008538121,0.0004555159,0.0007136181,0.0002208255,0.00002474351,0.0004627595],"genre_scores_gemma":[0.9991795,0.00001149949,0.00009663864,0.000035845,0.00008767017,0.0001377933,0.00007188329,0.000006773715,0.0003723581],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9851649,"threshold_uncertainty_score":0.4383727,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01589346132133927,"score_gpt":0.298496630717028,"score_spread":0.2826031693956887,"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."}}