{"id":"W3134042610","doi":"10.1007/978-3-030-68799-1_5","title":"Use of Frequency Domain for Complexity Reduction of Convolutional Neural Networks","year":2021,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University","funders":"","keywords":"Fast Fourier transform; Convolutional neural network; Computer science; Split-radix FFT algorithm; Reduction (mathematics); Computation; Convolution (computer science); Prime-factor FFT algorithm; Computational complexity theory; Quantization (signal processing); Frequency domain; Algorithm; Pruning; Rader's FFT algorithm; Redundancy (engineering); Twiddle factor; Multiplication (music); Parallel computing; Artificial neural network; Fourier transform; Mathematics; Artificial intelligence; Fractional Fourier transform; Fourier analysis","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"],"consensus_categories":[],"category_scores_codex":[0.0003580058,0.000346915,0.0005756122,0.0003366048,0.0001862213,0.00009133686,0.001641796,0.000226622,0.000008594568],"category_scores_gemma":[0.00007139321,0.0003533031,0.0001975262,0.0007607549,0.001494452,0.0006061993,0.0006790277,0.0004579627,6.065845e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001762218,"about_ca_system_score_gemma":0.0003061007,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001850464,"about_ca_topic_score_gemma":0.0000364043,"domain_scores_codex":[0.9970673,0.00004241987,0.0007497149,0.001112832,0.0005876436,0.000440078],"domain_scores_gemma":[0.9965855,0.0007580426,0.0006657167,0.001200777,0.0006858408,0.0001041558],"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":[0.00001033516,0.00004203611,0.00003598051,0.00004265967,0.00001367975,0.000004274835,0.0001018776,0.3859333,0.001460482,0.5358217,0.00002372829,0.07651],"study_design_scores_gemma":[0.0001344074,0.00009083528,0.0001377036,0.0001172247,0.000006248196,0.00004628762,1.003942e-7,0.5881864,0.0006923185,0.4102271,0.0001236573,0.0002377493],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003584969,0.0004465887,0.9967439,0.000530863,0.001105402,0.0006388663,0.00003263917,0.00005735532,0.00008593486],"genre_scores_gemma":[0.1416964,0.00003235394,0.8576452,0.0001848098,0.0003233639,0.00002376861,0.00003503006,0.00002082832,0.00003822103],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2022531,"threshold_uncertainty_score":0.9998919,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05515196108872011,"score_gpt":0.2787569622757698,"score_spread":0.2236050011870497,"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."}}