{"id":"W2154515525","doi":"10.1109/ijcnn.1992.226922","title":"Architectural synthesis for digital neural networks","year":2003,"lang":"en","type":"article","venue":"","topic":"Advanced Memory and Neural Computing","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Artificial neural network; Computer architecture; Very-large-scale integration; Backpropagation; Digital signal processing; Implementation; Physical neural network; Artificial intelligence; Embedded system; Computer engineering; Computer hardware; Time delay neural network; Types of artificial neural networks; Software engineering","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":[0.0003399174,0.0005825712,0.0003017828,0.0005312463,0.0003757762,0.0007535352,0.0005827731,0.0004688627,0.007101806],"category_scores_gemma":[0.0009765434,0.0003177662,0.0006479303,0.0004185079,0.0004093038,0.0006303783,0.0005092975,0.0005755043,0.001192157],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008463488,"about_ca_system_score_gemma":0.0007866743,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001540793,"about_ca_topic_score_gemma":0.003827548,"domain_scores_codex":[0.9997192,0.00007569772,0.00002412224,0.00003471046,0.0001170941,0.00002909254],"domain_scores_gemma":[0.9997498,0.0001085926,0.00002052945,0.00004261585,0.00007132885,0.000007134263],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00007226607,0.0000349877,0.0002501347,0.0004994071,0.00005231311,0.0001353354,0.0001081255,0.5379063,0.03002791,0.2397056,0.003971586,0.1872362],"study_design_scores_gemma":[0.00004726357,0.00008242111,0.0001263711,0.00007485228,0.00003508289,0.00009304268,0.00004185503,0.849201,0.0166763,0.09440808,0.03919579,0.00001788199],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00813899,0.0007515174,0.9661983,0.0002240434,0.000111058,0.000100038,0.0001619183,0.0009876211,0.02332648],"genre_scores_gemma":[0.2412322,0.001315314,0.7453291,0.0001969457,0.00007288492,0.0005344403,0.0005053492,0.0002537956,0.01055987],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007101806,"threshold_uncertainty_score":0.02375787,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0116277636847276,"score_gpt":0.2071285885359028,"score_spread":0.1955008248511752,"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."}}