{"id":"W2582160025","doi":"10.47839/ijc.18.1.1270","title":"A DEEP CONVOLUTIONAL AUTO-ENCODER WITH POOLING – UNPOOLING LAYERS IN CAFFE","year":2019,"lang":"en","type":"preprint","venue":"International Journal of Computing","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Lethbridge","funders":"Pohang University of Science and Technology","keywords":"MNIST database; Pooling; Deep learning; Computer science; Artificial intelligence; Convolutional neural network; Encoder; Pattern recognition (psychology); Dimensionality reduction; Perceptron; Autoencoder; Cluster analysis; Artificial neural network","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":[0.000611641,0.0002411705,0.000388708,0.0004487629,0.00006374758,0.0003883674,0.002228721,0.0001274173,0.000007833853],"category_scores_gemma":[0.00004203836,0.0002111883,0.0001787448,0.0002234008,0.00004238599,0.0003287424,0.0009918259,0.001135722,0.000009386467],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003021662,"about_ca_system_score_gemma":0.000507854,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004665498,"about_ca_topic_score_gemma":0.00001626064,"domain_scores_codex":[0.9975049,0.00008168738,0.0008412565,0.0003763695,0.0009093375,0.000286465],"domain_scores_gemma":[0.997319,0.0003466482,0.001146893,0.0002791014,0.0008118651,0.00009651366],"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":[0.00002135291,0.0000621509,0.003814193,0.00001428056,0.0001273897,0.000129229,0.000449059,0.9804072,0.00007584148,0.007946449,0.0001134387,0.006839417],"study_design_scores_gemma":[0.0006396571,0.00003839358,0.006153003,0.0008970292,0.00001245397,0.0004405531,0.00004526921,0.987353,0.00005255123,0.003679737,0.0004486377,0.0002397663],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1480359,0.00032456,0.8468958,0.002015325,0.002133798,0.0001412503,0.0000022607,0.00003368708,0.0004174123],"genre_scores_gemma":[0.9255165,0.0000382919,0.07308825,0.0004083912,0.0009006175,0.00000226761,0.000006086093,0.0000166658,0.00002287168],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7774807,"threshold_uncertainty_score":0.861201,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0139874653528637,"score_gpt":0.2764441205441974,"score_spread":0.2624566551913337,"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."}}