{"id":"W4400066938","doi":"10.1088/2634-4386/ad5c97","title":"Efficient sparse spiking auto-encoder for reconstruction, denoising and classification","year":2024,"lang":"en","type":"article","venue":"Neuromorphic Computing and Engineering","topic":"Advanced Memory and Neural Computing","field":"Engineering","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; York University","funders":"","keywords":"MNIST database; Spiking neural network; Neuromorphic engineering; Computer science; Artificial intelligence; Encoder; Pattern recognition (psychology); Inference; Noise reduction; Encoding (memory); Spike (software development); Noise (video); Machine learning; Deep learning; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004226086,0.0003725611,0.0003712504,0.0002982259,0.0001710957,0.0004848232,0.0008174703,0.0004003927,0.001481881],"category_scores_gemma":[0.001453066,0.0001976356,0.000276666,0.0003212791,0.0002595274,0.0006729997,0.0005996928,0.0007143803,0.0005339393],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000328177,"about_ca_system_score_gemma":0.0007245109,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001713081,"about_ca_topic_score_gemma":0.004293112,"domain_scores_codex":[0.9997516,0.00003138618,0.00001776787,0.00004600091,0.0001242162,0.00002901839],"domain_scores_gemma":[0.9994245,0.000173946,0.00005098565,0.0001334471,0.0001900797,0.00002710277],"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":[0.00031936,0.0002261384,0.003375091,0.000163387,0.0001011077,0.0001810671,0.00009497587,0.22617,0.1192053,0.0147671,0.005902588,0.6294939],"study_design_scores_gemma":[0.000005025393,0.0000337682,0.0003268585,0.00000637932,0.000008920717,0.00005753546,0.000006601441,0.9535309,0.04306959,0.001782487,0.001165359,0.000006631533],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08126874,0.0002637867,0.9117216,0.0002457431,0.00007483805,0.00004286953,0.0003260246,0.003243584,0.002812763],"genre_scores_gemma":[0.7000413,0.0002273153,0.2942678,0.0001827857,0.00003292282,0.00006496619,0.000642898,0.0001277803,0.0044122],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.001713081,"threshold_uncertainty_score":0.004957438,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02996621757660762,"score_gpt":0.2326322652935255,"score_spread":0.2026660477169179,"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."}}