Thomas Randazzo

Array ( [id] => 17729935 [patent_doc_number] => 11386327 [patent_country] => US [patent_kind] => B2 [patent_issue_date] => 2022-07-12 [patent_title] => Block-diagonal hessian-free optimization for recurrent and convolutional neural networks [patent_app_type] => utility [patent_app_number] => 15/983782 [patent_app_country] => US [patent_app_date] => 2018-05-18 [patent_effective_date] => 0000-00-00 [patent_drawing_sheets_cnt] => 8 [patent_figures_cnt] => 8 [patent_no_of_words] => 6358 [patent_no_of_claims] => 20 [patent_no_of_ind_claims] => 3 [patent_words_short_claim] => 210 [patent_maintenance] => 1 [patent_no_of_assignments] => 0 [patent_current_assignee] =>[type] => patent [pdf_file] =>[firstpage_image] =>[orig_patent_app_number] => 15983782 [rel_patent_id] =>[rel_patent_doc_number] =>)

Array ( [id] => 14283245 [patent_doc_number] => 20190138907 [patent_country] => US [patent_kind] => A1 [patent_issue_date] => 2019-05-09 [patent_title] => Unsupervised Deep Learning Biological Neural Networks [patent_app_type] => utility [patent_app_number] => 15/983078 [patent_app_country] => US [patent_app_date] => 2018-05-17 [patent_effective_date] => 0000-00-00 [patent_drawing_sheets_cnt] => 0 [patent_figures_cnt] => 0 [patent_no_of_words] => 15212 [patent_no_of_claims] => 0 [patent_no_of_ind_claims] => -18 [patent_words_short_claim] => 47 [patent_maintenance] => 1 [patent_no_of_assignments] => 0 [patent_current_assignee] =>[type] => publication [pdf_file] =>[firstpage_image] =>[orig_patent_app_number] => 15983078 [rel_patent_id] =>[rel_patent_doc_number] =>)

Array ( [id] => 14645451 [patent_doc_number] => 10367479 [patent_country] => US [patent_kind] => B2 [patent_issue_date] => 2019-07-30 [patent_title] => Method and apparatus to reduce noise in CT data acquisition systems [patent_app_type] => utility [patent_app_number] => 15/980791 [patent_app_country] => US [patent_app_date] => 2018-05-16 [patent_effective_date] => 0000-00-00 [patent_drawing_sheets_cnt] => 7 [patent_figures_cnt] => 7 [patent_no_of_words] => 6745 [patent_no_of_claims] => 15 [patent_no_of_ind_claims] => 4 [patent_words_short_claim] => 101 [patent_maintenance] => 1 [patent_no_of_assignments] => 0 [patent_current_assignee] =>[type] => patent [pdf_file] =>[firstpage_image] =>[orig_patent_app_number] => 15980791 [rel_patent_id] =>[rel_patent_doc_number] =>)

Array ( [id] => 17824901 [patent_doc_number] => 11429849 [patent_country] => US [patent_kind] => B2 [patent_issue_date] => 2022-08-30 [patent_title] => Deep compressed network [patent_app_type] => utility [patent_app_number] => 15/977477 [patent_app_country] => US [patent_app_date] => 2018-05-11 [patent_effective_date] => 0000-00-00 [patent_drawing_sheets_cnt] => 9 [patent_figures_cnt] => 13 [patent_no_of_words] => 9207 [patent_no_of_claims] => 21 [patent_no_of_ind_claims] => 4 [patent_words_short_claim] => 171 [patent_maintenance] => 1 [patent_no_of_assignments] => 0 [patent_current_assignee] =>[type] => patent [pdf_file] =>[firstpage_image] =>[orig_patent_app_number] => 15977477 [rel_patent_id] =>[rel_patent_doc_number] =>)

Array ( [id] => 14266003 [patent_doc_number] => 10282567 [patent_country] => US [patent_kind] => B2 [patent_issue_date] => 2019-05-07 [patent_title] => High voltage inductive adder [patent_app_type] => utility [patent_app_number] => 15/973519 [patent_app_country] => US [patent_app_date] => 2018-05-07 [patent_effective_date] => 0000-00-00 [patent_drawing_sheets_cnt] => 13 [patent_figures_cnt] => 14 [patent_no_of_words] => 6626 [patent_no_of_claims] => 20 [patent_no_of_ind_claims] => 2 [patent_words_short_claim] => 149 [patent_maintenance] => 1 [patent_no_of_assignments] => 0 [patent_current_assignee] =>[type] => patent [pdf_file] =>[firstpage_image] =>[orig_patent_app_number] => 15973519 [rel_patent_id] =>[rel_patent_doc_number] =>)

Array ( [id] => 13809161 [patent_doc_number] => 10181850 [patent_country] => US [patent_kind] => B2 [patent_issue_date] => 2019-01-15 [patent_title] => High throw-count RF switch [patent_app_type] => utility [patent_app_number] => 15/970778 [patent_app_country] => US [patent_app_date] => 2018-05-03 [patent_effective_date] => 0000-00-00 [patent_drawing_sheets_cnt] => 7 [patent_figures_cnt] => 9 [patent_no_of_words] => 7037 [patent_no_of_claims] => 20 [patent_no_of_ind_claims] => 2 [patent_words_short_claim] => 100 [patent_maintenance] => 1 [patent_no_of_assignments] => 0 [patent_current_assignee] =>[type] => patent [pdf_file] =>[firstpage_image] =>[orig_patent_app_number] => 15970778 [rel_patent_id] =>[rel_patent_doc_number] =>)

Array ( [id] => 15091397 [patent_doc_number] => 20190340510 [patent_country] => US [patent_kind] => A1 [patent_issue_date] => 2019-11-07 [patent_title] => SPARSIFYING NEURAL NETWORK MODELS [patent_app_type] => utility [patent_app_number] => 15/967835 [patent_app_country] => US [patent_app_date] => 2018-05-01 [patent_effective_date] => 0000-00-00 [patent_drawing_sheets_cnt] => 0 [patent_figures_cnt] => 0 [patent_no_of_words] => 4362 [patent_no_of_claims] => 0 [patent_no_of_ind_claims] => -17 [patent_words_short_claim] => 103 [patent_maintenance] => 1 [patent_no_of_assignments] => 0 [patent_current_assignee] =>[type] => publication [pdf_file] =>[firstpage_image] =>[orig_patent_app_number] => 15967835 [rel_patent_id] =>[rel_patent_doc_number] =>)

Array ( [id] => 17380328 [patent_doc_number] => 11238346 [patent_country] => US [patent_kind] => B2 [patent_issue_date] => 2022-02-01 [patent_title] => Learning a truncation rank of singular value decomposed matrices representing weight tensors in neural networks [patent_app_type] => utility [patent_app_number] => 15/962996 [patent_app_country] => US [patent_app_date] => 2018-04-25 [patent_effective_date] => 0000-00-00 [patent_drawing_sheets_cnt] => 10 [patent_figures_cnt] => 10 [patent_no_of_words] => 9515 [patent_no_of_claims] => 29 [patent_no_of_ind_claims] => 4 [patent_words_short_claim] => 121 [patent_maintenance] => 1 [patent_no_of_assignments] => 0 [patent_current_assignee] =>[type] => patent [pdf_file] =>[firstpage_image] =>[orig_patent_app_number] => 15962996 [rel_patent_id] =>[rel_patent_doc_number] =>)

Array ( [id] => 13379435 [patent_doc_number] => 20180241259 [patent_country] => US [patent_kind] => A1 [patent_issue_date] => 2018-08-23 [patent_title] => WIRELESS POWER SUPPLY SYSTEM [patent_app_type] => utility [patent_app_number] => 15/962787 [patent_app_country] => US [patent_app_date] => 2018-04-25 [patent_effective_date] => 0000-00-00 [patent_drawing_sheets_cnt] => 0 [patent_figures_cnt] => 0 [patent_no_of_words] => 24736 [patent_no_of_claims] => 0 [patent_no_of_ind_claims] => -5 [patent_words_short_claim] => 138 [patent_maintenance] => 1 [patent_no_of_assignments] => 0 [patent_current_assignee] =>[type] => publication [pdf_file] =>[firstpage_image] =>[orig_patent_app_number] => 15962787 [rel_patent_id] =>[rel_patent_doc_number] =>)

Array ( [id] => 15043843 [patent_doc_number] => 20190332926 [patent_country] => US [patent_kind] => A1 [patent_issue_date] => 2019-10-31 [patent_title] => Backpressure for Accelerated Deep Learning [patent_app_type] => utility [patent_app_number] => 16/088706 [patent_app_country] => US [patent_app_date] => 2018-04-17 [patent_effective_date] => 0000-00-00 [patent_drawing_sheets_cnt] => 0 [patent_figures_cnt] => 0 [patent_no_of_words] => 60477 [patent_no_of_claims] => 0 [patent_no_of_ind_claims] => -42 [patent_words_short_claim] => 144 [patent_maintenance] => 1 [patent_no_of_assignments] => 0 [patent_current_assignee] =>[type] => publication [pdf_file] =>[firstpage_image] =>[orig_patent_app_number] => 16088706 [rel_patent_id] =>[rel_patent_doc_number] =>)

Array ( [id] => 14967557 [patent_doc_number] => 20190311257 [patent_country] => US [patent_kind] => A1 [patent_issue_date] => 2019-10-10 [patent_title] => COORDINATED HETEROGENEOUS PROCESSING OF TRAINING DATA FOR DEEP NEURAL NETWORKS [patent_app_type] => utility [patent_app_number] => 15/945647 [patent_app_country] => US [patent_app_date] => 2018-04-04 [patent_effective_date] => 0000-00-00 [patent_drawing_sheets_cnt] => 0 [patent_figures_cnt] => 0 [patent_no_of_words] => 5520 [patent_no_of_claims] => 0 [patent_no_of_ind_claims] => -17 [patent_words_short_claim] => 70 [patent_maintenance] => 1 [patent_no_of_assignments] => 0 [patent_current_assignee] =>[type] => publication [pdf_file] =>[firstpage_image] =>[orig_patent_app_number] => 15945647 [rel_patent_id] =>[rel_patent_doc_number] =>)

Array ( [id] => 17365341 [patent_doc_number] => 11232364 [patent_country] => US [patent_kind] => B2 [patent_issue_date] => 2022-01-25 [patent_title] => Automated rule recommendation engine [patent_app_type] => utility [patent_app_number] => 15/944701 [patent_app_country] => US [patent_app_date] => 2018-04-03 [patent_effective_date] => 0000-00-00 [patent_drawing_sheets_cnt] => 5 [patent_figures_cnt] => 5 [patent_no_of_words] => 6266 [patent_no_of_claims] => 19 [patent_no_of_ind_claims] => 3 [patent_words_short_claim] => 172 [patent_maintenance] => 1 [patent_no_of_assignments] => 0 [patent_current_assignee] =>[type] => patent [pdf_file] =>[firstpage_image] =>[orig_patent_app_number] => 15944701 [rel_patent_id] =>[rel_patent_doc_number] =>)

Array ( [id] => 14936297 [patent_doc_number] => 20190303787 [patent_country] => US [patent_kind] => A1 [patent_issue_date] => 2019-10-03 [patent_title] => ADAPTIVE LEARNING RATE SCHEDULE IN DISTRIBUTED STOCHASTIC GRADIENT DESCENT [patent_app_type] => utility [patent_app_number] => 15/938830 [patent_app_country] => US [patent_app_date] => 2018-03-28 [patent_effective_date] => 0000-00-00 [patent_drawing_sheets_cnt] => 0 [patent_figures_cnt] => 0 [patent_no_of_words] => 4245 [patent_no_of_claims] => 0 [patent_no_of_ind_claims] => -17 [patent_words_short_claim] => 86 [patent_maintenance] => 1 [patent_no_of_assignments] => 0 [patent_current_assignee] =>[type] => publication [pdf_file] =>[firstpage_image] =>[orig_patent_app_number] => 15938830 [rel_patent_id] =>[rel_patent_doc_number] =>)

Array ( [id] => 17077227 [patent_doc_number] => 11113630 [patent_country] => US [patent_kind] => B2 [patent_issue_date] => 2021-09-07 [patent_title] => Computer architecture for training a correlithm object processing system [patent_app_type] => utility [patent_app_number] => 15/927584 [patent_app_country] => US [patent_app_date] => 2018-03-21 [patent_effective_date] => 0000-00-00 [patent_drawing_sheets_cnt] => 8 [patent_figures_cnt] => 8 [patent_no_of_words] => 13135 [patent_no_of_claims] => 20 [patent_no_of_ind_claims] => 3 [patent_words_short_claim] => 256 [patent_maintenance] => 1 [patent_no_of_assignments] => 0 [patent_current_assignee] =>[type] => patent [pdf_file] =>[firstpage_image] =>[orig_patent_app_number] => 15927584 [rel_patent_id] =>[rel_patent_doc_number] =>)

Array ( [id] => 14770717 [patent_doc_number] => 10396771 [patent_country] => US [patent_kind] => B2 [patent_issue_date] => 2019-08-27 [patent_title] => Voltage supply circuits and controlling methods therefor [patent_app_type] => utility [patent_app_number] => 15/921513 [patent_app_country] => US [patent_app_date] => 2018-03-14 [patent_effective_date] => 0000-00-00 [patent_drawing_sheets_cnt] => 8 [patent_figures_cnt] => 10 [patent_no_of_words] => 4312 [patent_no_of_claims] => 20 [patent_no_of_ind_claims] => 2 [patent_words_short_claim] => 151 [patent_maintenance] => 1 [patent_no_of_assignments] => 0 [patent_current_assignee] =>[type] => patent [pdf_file] =>[firstpage_image] =>[orig_patent_app_number] => 15921513 [rel_patent_id] =>[rel_patent_doc_number] =>)

Array ( [id] => 14348549 [patent_doc_number] => 20190156247 [patent_country] => US [patent_kind] => A1 [patent_issue_date] => 2019-05-23 [patent_title] => DYNAMIC ACCURACY-BASED DEPLOYMENT AND MONITORING OF MACHINE LEARNING MODELS IN PROVIDER NETWORKS [patent_app_type] => utility [patent_app_number] => 15/919628 [patent_app_country] => US [patent_app_date] => 2018-03-13 [patent_effective_date] => 0000-00-00 [patent_drawing_sheets_cnt] => 0 [patent_figures_cnt] => 0 [patent_no_of_words] => 19500 [patent_no_of_claims] => 0 [patent_no_of_ind_claims] => -17 [patent_words_short_claim] => 111 [patent_maintenance] => 1 [patent_no_of_assignments] => 0 [patent_current_assignee] =>[type] => publication [pdf_file] =>[firstpage_image] =>[orig_patent_app_number] => 15919628 [rel_patent_id] =>[rel_patent_doc_number] =>)

Array ( [id] => 13379703 [patent_doc_number] => 20180241393 [patent_country] => US [patent_kind] => A1 [patent_issue_date] => 2018-08-23 [patent_title] => High Speed and High Voltage Driver [patent_app_type] => utility [patent_app_number] => 15/918933 [patent_app_country] => US [patent_app_date] => 2018-03-12 [patent_effective_date] => 0000-00-00 [patent_drawing_sheets_cnt] => 0 [patent_figures_cnt] => 0 [patent_no_of_words] => 10286 [patent_no_of_claims] => 0 [patent_no_of_ind_claims] => -20 [patent_words_short_claim] => 2 [patent_maintenance] => 1 [patent_no_of_assignments] => 0 [patent_current_assignee] =>[type] => publication [pdf_file] =>[firstpage_image] =>[orig_patent_app_number] => 15918933 [rel_patent_id] =>[rel_patent_doc_number] =>)

Array ( [id] => 13418343 [patent_doc_number] => 20180260714 [patent_country] => US [patent_kind] => A1 [patent_issue_date] => 2018-09-13 [patent_title] => GLOBAL OPTIMIZATION, SEARCH AND MACHINE LEARNING METHOD BASED ON THE LAMARCKIAN PRINCIPLE OF INHERITANCE OF ACQUIRED CHARACTERISTICS [patent_app_type] => utility [patent_app_number] => 15/917142 [patent_app_country] => US [patent_app_date] => 2018-03-09 [patent_effective_date] => 0000-00-00 [patent_drawing_sheets_cnt] => 0 [patent_figures_cnt] => 0 [patent_no_of_words] => 5663 [patent_no_of_claims] => 0 [patent_no_of_ind_claims] => -18 [patent_words_short_claim] => 43 [patent_maintenance] => 1 [patent_no_of_assignments] => 0 [patent_current_assignee] =>[type] => publication [pdf_file] =>[firstpage_image] =>[orig_patent_app_number] => 15917142 [rel_patent_id] =>[rel_patent_doc_number] =>)

Array ( [id] => 14783203 [patent_doc_number] => 20190266499 [patent_country] => US [patent_kind] => A1 [patent_issue_date] => 2019-08-29 [patent_title] => INDEPENDENT SPARSE SUB-SYSTEM CALCULATIONS FOR DYNAMIC STATE ESTIMATION IN EMBEDDED SYSTEMS [patent_app_type] => utility [patent_app_number] => 15/907634 [patent_app_country] => US [patent_app_date] => 2018-02-28 [patent_effective_date] => 0000-00-00 [patent_drawing_sheets_cnt] => 0 [patent_figures_cnt] => 0 [patent_no_of_words] => 9291 [patent_no_of_claims] => 0 [patent_no_of_ind_claims] => -17 [patent_words_short_claim] => 139 [patent_maintenance] => 1 [patent_no_of_assignments] => 0 [patent_current_assignee] =>[type] => publication [pdf_file] =>[firstpage_image] =>[orig_patent_app_number] => 15907634 [rel_patent_id] =>[rel_patent_doc_number] =>)

Array ( [id] => 13993607 [patent_doc_number] => 20190065961 [patent_country] => US [patent_kind] => A1 [patent_issue_date] => 2019-02-28 [patent_title] => Unsupervised Deep Learning Biological Neural Networks [patent_app_type] => utility [patent_app_number] => 15/903729 [patent_app_country] => US [patent_app_date] => 2018-02-23 [patent_effective_date] => 0000-00-00 [patent_drawing_sheets_cnt] => 0 [patent_figures_cnt] => 0 [patent_no_of_words] => 10219 [patent_no_of_claims] => 0 [patent_no_of_ind_claims] => -18 [patent_words_short_claim] => 47 [patent_maintenance] => 1 [patent_no_of_assignments] => 0 [patent_current_assignee] =>[type] => publication [pdf_file] =>[firstpage_image] =>[orig_patent_app_number] => 15903729 [rel_patent_id] =>[rel_patent_doc_number] =>)