{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/rmsprop/papers/5","list_of":"/method/rmsprop","method":"RMSProp","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":5,"pages_in_order":6,"rows_per_page":100,"rows":[401,500],"of":519,"counts":{"archive_papers_tagged":519,"with_a_code_link":236,"where_syntology_ran_a_sample":70,"not_listed_spam_title":0,"listed":519,"listed_where_code_ran":70,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":62,"every_run_a_failure_of_syntologys_instrument":8,"listed_with_a_run_with_no_instrument_failure":62,"listed_every_run_a_failure_of_syntologys_instrument":8,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/method/rmsprop","prev":"/method/rmsprop/papers/4","next":"/method/rmsprop/papers/6","papers":[{"paper":null,"slug":"introducing-fuzzy-layers-for-deep-learning","title":"Introducing Fuzzy Layers for Deep Learning","date":"2020-02-21","arxiv_id":"2003.00880","n_code_links":0,"syntology":null},{"paper":"/paper/maxup-a-simple-way-to-improve-generalization","slug":"maxup-a-simple-way-to-improve-generalization","title":"MaxUp: A Simple Way to Improve Generalization of Neural Network Training","date":"2020-02-20","arxiv_id":"2002.09024","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":null}},{"paper":null,"slug":"exponential-discretization-of-weights-of","title":"Exponential discretization of weights of neural network connections in pre-trained neural networks","date":"2020-02-03","arxiv_id":"2002.00623","n_code_links":0,"syntology":null},{"paper":null,"slug":"gradient-descent-with-momentum-to-accelerate","title":"Gradient descent with momentum --- to accelerate or to super-accelerate?","date":"2020-01-17","arxiv_id":"2001.06472","n_code_links":0,"syntology":null},{"paper":"/paper/zeroq-a-novel-zero-shot-quantization","slug":"zeroq-a-novel-zero-shot-quantization","title":"ZeroQ: A Novel Zero Shot Quantization Framework","date":"2020-01-01","arxiv_id":"2001.00281","n_code_links":3,"syntology":{"ran":7,"of":19,"n_ran_checked":4,"n_instrument":3,"unverified":12,"pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 12 unverified","official":{"repos":["amirgholami/ZeroQ"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"attention-based-face-antispoofing-of-rgb","title":"Attention-Based Face AntiSpoofing of RGB Images, using a Minimal End-2-End Neural Network","date":"2019-12-18","arxiv_id":"1912.08870","n_code_links":0,"syntology":null},{"paper":"/paper/parameter-continuation-methods-for-the","slug":"parameter-continuation-methods-for-the","title":"Parameter Continuation Methods for the Optimization of Deep Neural Networks","date":"2019-12-16","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/linear-mode-connectivity-and-the-lottery","slug":"linear-mode-connectivity-and-the-lottery","title":"Linear Mode Connectivity and the Lottery Ticket Hypothesis","date":"2019-12-11","arxiv_id":"1912.05671","n_code_links":2,"syntology":null},{"paper":"/paper/scratch-that-an-evolution-based-adversarial","slug":"scratch-that-an-evolution-based-adversarial","title":"Scratch that! An Evolution-based Adversarial Attack against Neural Networks","date":"2019-12-05","arxiv_id":"1912.02316","n_code_links":1,"syntology":null},{"paper":null,"slug":"impact-importance-weighted-asynchronous-1","title":"IMPACT: Importance Weighted Asynchronous Architectures with Clipped Target Networks","date":"2019-11-30","arxiv_id":"1912.00167","n_code_links":0,"syntology":null},{"paper":null,"slug":"structured-multi-hashing-for-model","title":"Structured Multi-Hashing for Model Compression","date":"2019-11-25","arxiv_id":"1911.11177","n_code_links":0,"syntology":null},{"paper":"/paper/adversarial-examples-improve-image","slug":"adversarial-examples-improve-image","title":"Adversarial Examples Improve Image Recognition","date":"2019-11-21","arxiv_id":"1911.09665","n_code_links":6,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["tensorflow/tpu"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/fast-sparse-convnets-1","slug":"fast-sparse-convnets-1","title":"Fast Sparse ConvNets","date":"2019-11-21","arxiv_id":"1911.09723","n_code_links":5,"syntology":null},{"paper":"/paper/filter-response-normalization-layer","slug":"filter-response-normalization-layer","title":"Filter Response Normalization Layer: Eliminating Batch Dependence in the Training of Deep Neural Networks","date":"2019-11-21","arxiv_id":"1911.09737","n_code_links":16,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/efficientdet-scalable-and-efficient-object","slug":"efficientdet-scalable-and-efficient-object","title":"EfficientDet: Scalable and Efficient Object Detection","date":"2019-11-20","arxiv_id":"1911.09070","n_code_links":64,"syntology":{"ran":55,"of":70,"n_ran_checked":48,"n_instrument":7,"unverified":15,"pointer_only":7,"phrase":"55 ran (of which 1 constructed an object rather than computing a result; 48 with no instrument failure: 4 honoured, 0 violated, 44 with no contract checked; 7 where Syntology's instrument failed) · 15 unverified","official":{"repos":["google/automl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"experimental-exploration-of-compact","title":"Experimental Exploration of Compact Convolutional Neural Network Architectures for Non-temporal Real-time Fire Detection","date":"2019-11-20","arxiv_id":"1911.09010","n_code_links":0,"syntology":null},{"paper":"/paper/self-training-with-noisy-student-improves","slug":"self-training-with-noisy-student-improves","title":"Self-training with Noisy Student improves ImageNet classification","date":"2019-11-11","arxiv_id":"1911.04252","n_code_links":13,"syntology":{"ran":13,"of":24,"n_ran_checked":10,"n_instrument":3,"unverified":11,"pointer_only":2,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 11 unverified","official":{"repos":["google-research/noisystudent","tensorflow/tpu"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":10,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"predictive-modeling-of-brain-tumor-a-deep","title":"Predictive modeling of brain tumor: A Deep learning approach","date":"2019-11-06","arxiv_id":"1911.02265","n_code_links":0,"syntology":null},{"paper":null,"slug":"identification-of-primary-angle-closure-on-as","title":"Identification of primary angle-closure on AS-OCT images with Convolutional Neural Networks","date":"2019-10-23","arxiv_id":"1910.10414","n_code_links":0,"syntology":null},{"paper":null,"slug":"establishing-an-evaluation-metric-to-quantify","title":"Establishing an Evaluation Metric to Quantify Climate Change Image Realism","date":"2019-10-22","arxiv_id":"1910.10143","n_code_links":0,"syntology":null},{"paper":null,"slug":"implementation-of-a-modified-nesterovs","title":"Implementation of a modified Nesterov's Accelerated quasi-Newton Method on Tensorflow","date":"2019-10-21","arxiv_id":"1910.09158","n_code_links":0,"syntology":null},{"paper":null,"slug":"icps-net-an-end-to-end-rgb-based-indoor","title":"ICPS-net: An End-to-End RGB-based Indoor Camera Positioning System using deep convolutional neural networks","date":"2019-10-14","arxiv_id":"1910.06219","n_code_links":0,"syntology":null},{"paper":"/paper/torchbeast-a-pytorch-platform-for-distributed","slug":"torchbeast-a-pytorch-platform-for-distributed","title":"TorchBeast: A PyTorch Platform for Distributed RL","date":"2019-10-08","arxiv_id":"1910.03552","n_code_links":3,"syntology":{"ran":6,"of":9,"n_ran_checked":2,"n_instrument":4,"unverified":3,"pointer_only":3,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","official":{"repos":["heiner/scalable_agent"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/randaugment-practical-data-augmentation-with","slug":"randaugment-practical-data-augmentation-with","title":"RandAugment: Practical automated data augmentation with a reduced search space","date":"2019-09-30","arxiv_id":"1909.13719","n_code_links":19,"syntology":{"ran":58,"of":65,"n_ran_checked":7,"n_instrument":51,"unverified":7,"pointer_only":17,"phrase":"58 ran (of which 1 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 51 where Syntology's instrument failed) · 7 unverified","official":null}},{"paper":null,"slug":"gdp-generalized-device-placement-for-dataflow","title":"GDP: Generalized Device Placement for Dataflow Graphs","date":"2019-09-28","arxiv_id":"1910.01578","n_code_links":0,"syntology":null},{"paper":"/paper/a-closer-look-at-network-resolution-for","slug":"a-closer-look-at-network-resolution-for","title":"MutualNet: Adaptive ConvNet via Mutual Learning from Network Width and Resolution","date":"2019-09-27","arxiv_id":"1909.12978","n_code_links":2,"syntology":null},{"paper":"/paper/pretraining-boosts-out-of-domain-robustness","slug":"pretraining-boosts-out-of-domain-robustness","title":"Pretraining boosts out-of-domain robustness for pose estimation","date":"2019-09-24","arxiv_id":"1909.11229","n_code_links":1,"syntology":null},{"paper":"/paper/diffgrad-an-optimization-method-for","slug":"diffgrad-an-optimization-method-for","title":"diffGrad: An Optimization Method for Convolutional Neural Networks","date":"2019-09-12","arxiv_id":"1909.11015","n_code_links":1,"syntology":null},{"paper":"/paper/partitioned-integrators-for-thermodynamic","slug":"partitioned-integrators-for-thermodynamic","title":"Partitioned integrators for thermodynamic parameterization of neural networks","date":"2019-08-30","arxiv_id":"1908.11843","n_code_links":1,"syntology":null},{"paper":"/paper/scarletnas-bridging-the-gap-between","slug":"scarletnas-bridging-the-gap-between","title":"SCARLET-NAS: Bridging the Gap between Stability and Scalability in Weight-sharing Neural Architecture Search","date":"2019-08-16","arxiv_id":"1908.06022","n_code_links":1,"syntology":null},{"paper":null,"slug":"histographs-graphs-in-histopathology","title":"Histographs: Graphs in Histopathology","date":"2019-08-14","arxiv_id":"1908.05020","n_code_links":0,"syntology":null},{"paper":"/paper/on-the-variance-of-the-adaptive-learning-rate","slug":"on-the-variance-of-the-adaptive-learning-rate","title":"On the Variance of the Adaptive Learning Rate and Beyond","date":"2019-08-08","arxiv_id":"1908.03265","n_code_links":21,"syntology":{"ran":12,"of":13,"n_ran_checked":11,"n_instrument":1,"unverified":1,"pointer_only":1,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 2 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["LiyuanLucasLiu/RAdam"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/moga-searching-beyond-mobilenetv3","slug":"moga-searching-beyond-mobilenetv3","title":"MoGA: Searching Beyond MobileNetV3","date":"2019-08-04","arxiv_id":"1908.01314","n_code_links":2,"syntology":null},{"paper":null,"slug":"genetic-deep-learning-for-lung-cancer","title":"Genetic Deep Learning for Lung Cancer Screening","date":"2019-07-27","arxiv_id":"1907.11849","n_code_links":0,"syntology":null},{"paper":null,"slug":"rnn-based-online-handwritten-character","title":"RNN-based Online Handwritten Character Recognition Using Accelerometer and Gyroscope Data","date":"2019-07-24","arxiv_id":"1907.12935","n_code_links":0,"syntology":null},{"paper":null,"slug":"meta-descent-for-online-continual-prediction","title":"Meta-descent for Online, Continual Prediction","date":"2019-07-17","arxiv_id":"1907.07751","n_code_links":0,"syntology":null},{"paper":null,"slug":"deepda-lstm-based-deep-data-association","title":"DeepDA: LSTM-based Deep Data Association Network for Multi-Targets Tracking in Clutter","date":"2019-07-16","arxiv_id":"1907.09915","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-role-of-memory-in-stochastic-optimization","title":"The Role of Memory in Stochastic Optimization","date":"2019-07-02","arxiv_id":"1907.01678","n_code_links":0,"syntology":null},{"paper":"/paper/mimic-and-fool-a-task-agnostic-adversarial","slug":"mimic-and-fool-a-task-agnostic-adversarial","title":"Mimic and Fool: A Task Agnostic Adversarial Attack","date":"2019-06-11","arxiv_id":"1906.04606","n_code_links":1,"syntology":null},{"paper":"/paper/efficientnet-rethinking-model-scaling-for","slug":"efficientnet-rethinking-model-scaling-for","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","date":"2019-05-28","arxiv_id":"1905.11946","n_code_links":144,"syntology":{"ran":198,"of":302,"n_ran_checked":157,"n_instrument":41,"unverified":104,"pointer_only":113,"phrase":"198 ran (of which 73 constructed an object rather than computing a result; 157 with no instrument failure: 26 honoured, 2 violated, 129 with no contract checked; 41 where Syntology's instrument failed) · 104 unverified","official":{"repos":["tensorflow/tpu"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"paper":null,"slug":"190512413","title":"VecHGrad for Solving Accurately Complex Tensor Decomposition","date":"2019-05-24","arxiv_id":"1905.12413","n_code_links":0,"syntology":null},{"paper":null,"slug":"blockwise-adaptivity-faster-training-and","title":"Blockwise Adaptivity: Faster Training and Better Generalization in Deep Learning","date":"2019-05-23","arxiv_id":"1905.09899","n_code_links":0,"syntology":null},{"paper":null,"slug":"ellipsoidal-trust-region-methods-and-the","title":"Adaptive norms for deep learning with regularized Newton methods","date":"2019-05-22","arxiv_id":"1905.09201","n_code_links":0,"syntology":null},{"paper":"/paper/transfer-learning-based-detection-of-diabetic","slug":"transfer-learning-based-detection-of-diabetic","title":"Transfer Learning based Detection of Diabetic Retinopathy from Small Dataset","date":"2019-05-17","arxiv_id":"1905.07203","n_code_links":1,"syntology":null},{"paper":"/paper/sadam-a-variant-of-adam-for-strongly-convex","slug":"sadam-a-variant-of-adam-for-strongly-convex","title":"SAdam: A Variant of Adam for Strongly Convex Functions","date":"2019-05-08","arxiv_id":"1905.02957","n_code_links":1,"syntology":null},{"paper":"/paper/searching-for-mobilenetv3","slug":"searching-for-mobilenetv3","title":"Searching for MobileNetV3","date":"2019-05-06","arxiv_id":"1905.02244","n_code_links":67,"syntology":{"ran":86,"of":105,"n_ran_checked":75,"n_instrument":11,"unverified":19,"pointer_only":46,"phrase":"86 ran (of which 22 constructed an object rather than computing a result; 75 with no instrument failure: 6 honoured, 2 violated, 67 with no contract checked; 11 where Syntology's instrument failed) · 19 unverified","official":null}},{"paper":null,"slug":"a-unified-theory-of-adaptive-stochastic-1","title":"A unified theory of adaptive stochastic gradient descent as Bayesian filtering","date":"2019-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-combining-on-off-policy-methods-for","title":"Towards Combining On-Off-Policy Methods for Real-World Applications","date":"2019-04-24","arxiv_id":"1904.10642","n_code_links":0,"syntology":null},{"paper":"/paper/on-the-convergence-of-adam-and-beyond-1","slug":"on-the-convergence-of-adam-and-beyond-1","title":"On the Convergence of Adam and Beyond","date":"2019-04-19","arxiv_id":"1904.09237","n_code_links":3,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"double-transfer-learning-for-breast-cancer","title":"Double Transfer Learning for Breast Cancer Histopathologic Image Classification","date":"2019-04-16","arxiv_id":"1904.07834","n_code_links":0,"syntology":null},{"paper":"/paper/soft-conditional-computation","slug":"soft-conditional-computation","title":"CondConv: Conditionally Parameterized Convolutions for Efficient Inference","date":"2019-04-10","arxiv_id":"1904.04971","n_code_links":9,"syntology":null},{"paper":null,"slug":"understanding-unconventional-preprocessors-in","title":"Understanding Unconventional Preprocessors in Deep Convolutional Neural Networks for Face Identification","date":"2019-03-27","arxiv_id":"1904.00815","n_code_links":0,"syntology":null},{"paper":"/paper/adaptive-gradient-methods-with-dynamic-bound","slug":"adaptive-gradient-methods-with-dynamic-bound","title":"Adaptive Gradient Methods with Dynamic Bound of Learning Rate","date":"2019-02-26","arxiv_id":"1902.09843","n_code_links":5,"syntology":null},{"paper":null,"slug":"escaping-saddle-points-with-adaptive-gradient","title":"Escaping Saddle Points with Adaptive Gradient Methods","date":"2019-01-26","arxiv_id":"1901.09149","n_code_links":0,"syntology":null},{"paper":null,"slug":"accelerating-convolutional-neural-networks","title":"Accelerating Convolutional Neural Networks via Activation Map Compression","date":"2018-12-10","arxiv_id":"1812.04056","n_code_links":0,"syntology":null},{"paper":"/paper/adaptive-methods-for-nonconvex-optimization","slug":"adaptive-methods-for-nonconvex-optimization","title":"Adaptive Methods for Nonconvex Optimization","date":"2018-12-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/strike-with-a-pose-neural-networks-are-easily","slug":"strike-with-a-pose-neural-networks-are-easily","title":"Strike (with) a Pose: Neural Networks Are Easily Fooled by Strange Poses of Familiar Objects","date":"2018-11-28","arxiv_id":"1811.11553","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-sufficient-condition-for-convergences-of","title":"A Sufficient Condition for Convergences of Adam and RMSProp","date":"2018-11-23","arxiv_id":"1811.09358","n_code_links":0,"syntology":null},{"paper":"/paper/kalman-gradient-descent-adaptive-variance","slug":"kalman-gradient-descent-adaptive-variance","title":"Kalman Gradient Descent: Adaptive Variance Reduction in Stochastic Optimization","date":"2018-10-29","arxiv_id":"1810.12273","n_code_links":1,"syntology":null},{"paper":null,"slug":"finding-mixed-nash-equilibria-of-generative","title":"Finding Mixed Nash Equilibria of Generative Adversarial Networks","date":"2018-10-23","arxiv_id":"1811.02002","n_code_links":0,"syntology":null},{"paper":"/paper/deepweeds-a-multiclass-weed-species-image","slug":"deepweeds-a-multiclass-weed-species-image","title":"DeepWeeds: A Multiclass Weed Species Image Dataset for Deep Learning","date":"2018-10-09","arxiv_id":"1810.05726","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["AlexOlsen/DeepWeeds"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/preconditioner-on-matrix-lie-group-for-sgd","slug":"preconditioner-on-matrix-lie-group-for-sgd","title":"Preconditioner on Matrix Lie Group for SGD","date":"2018-09-26","arxiv_id":"1809.10232","n_code_links":2,"syntology":{"ran":5,"of":6,"n_ran_checked":1,"n_instrument":4,"unverified":1,"pointer_only":6,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","official":{"repos":["lixilinx/psgd_torch"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"discovering-low-precision-networks-close-to","title":"Discovering Low-Precision Networks Close to Full-Precision Networks for Efficient Embedded Inference","date":"2018-09-11","arxiv_id":"1809.04191","n_code_links":0,"syntology":null},{"paper":null,"slug":"dft-based-transformation-invariant-pooling","title":"DFT-based Transformation Invariant Pooling Layer for Visual Classification","date":"2018-09-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-convergence-of-adaptive-gradient","title":"On the Convergence of Adaptive Gradient Methods for Nonconvex Optimization","date":"2018-08-16","arxiv_id":"1808.05671","n_code_links":0,"syntology":null},{"paper":"/paper/backtracking-gradient-descent-method-for","slug":"backtracking-gradient-descent-method-for","title":"Backtracking gradient descent method for general $C^1$ functions, with applications to Deep Learning","date":"2018-08-15","arxiv_id":"1808.05160","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-the-convergence-of-weighted-adagrad-with","title":"A Unified Analysis of AdaGrad with Weighted Aggregation and Momentum Acceleration","date":"2018-08-10","arxiv_id":"1808.03408","n_code_links":0,"syntology":null},{"paper":"/paper/mnasnet-platform-aware-neural-architecture","slug":"mnasnet-platform-aware-neural-architecture","title":"MnasNet: Platform-Aware Neural Architecture Search for Mobile","date":"2018-07-31","arxiv_id":"1807.11626","n_code_links":29,"syntology":{"ran":4,"of":6,"n_ran_checked":3,"n_instrument":1,"unverified":2,"pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["tensorflow/tpu"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/a-unified-theory-of-adaptive-stochastic","slug":"a-unified-theory-of-adaptive-stochastic","title":"Bayesian filtering unifies adaptive and non-adaptive neural network optimization methods","date":"2018-07-19","arxiv_id":"1807.07540","n_code_links":1,"syntology":null},{"paper":null,"slug":"convergence-guarantees-for-rmsprop-and-adam","title":"Convergence guarantees for RMSProp and ADAM in non-convex optimization and an empirical comparison to Nesterov acceleration","date":"2018-07-18","arxiv_id":"1807.06766","n_code_links":0,"syntology":null},{"paper":"/paper/maximizing-invariant-data-perturbation-with","slug":"maximizing-invariant-data-perturbation-with","title":"Maximizing Invariant Data Perturbation with Stochastic Optimization","date":"2018-07-12","arxiv_id":"1807.05077","n_code_links":1,"syntology":null},{"paper":"/paper/representation-learning-with-contrastive","slug":"representation-learning-with-contrastive","title":"Representation Learning with Contrastive Predictive Coding","date":"2018-07-10","arxiv_id":"1807.03748","n_code_links":28,"syntology":{"ran":35,"of":45,"n_ran_checked":30,"n_instrument":5,"unverified":10,"pointer_only":22,"phrase":"35 ran (of which 21 constructed an object rather than computing a result; 30 with no instrument failure: 1 honoured, 0 violated, 29 with no contract checked; 5 where Syntology's instrument failed) · 10 unverified","official":null}},{"paper":"/paper/dank-learning-generating-memes-using-deep","slug":"dank-learning-generating-memes-using-deep","title":"Dank Learning: Generating Memes Using Deep Neural Networks","date":"2018-06-08","arxiv_id":"1806.04510","n_code_links":3,"syntology":null},{"paper":null,"slug":"geometry-aware-constrained-optimization","title":"Geometry Aware Constrained Optimization Techniques for Deep Learning","date":"2018-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/genattack-practical-black-box-attacks-with","slug":"genattack-practical-black-box-attacks-with","title":"GenAttack: Practical Black-box Attacks with Gradient-Free Optimization","date":"2018-05-28","arxiv_id":"1805.11090","n_code_links":3,"syntology":{"ran":5,"of":12,"n_ran_checked":5,"n_instrument":0,"unverified":7,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified","official":{"repos":["nesl/adversarial_genattack"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/nostalgic-adam-weighting-more-of-the-past","slug":"nostalgic-adam-weighting-more-of-the-past","title":"Nostalgic Adam: Weighting more of the past gradients when designing the adaptive learning rate","date":"2018-05-19","arxiv_id":"1805.07557","n_code_links":2,"syntology":null},{"paper":"/paper/adef-an-iterative-algorithm-to-construct","slug":"adef-an-iterative-algorithm-to-construct","title":"ADef: an Iterative Algorithm to Construct Adversarial Deformations","date":"2018-04-20","arxiv_id":"1804.07729","n_code_links":2,"syntology":{"ran":4,"of":4,"n_ran_checked":1,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"value-aware-quantization-for-training-and","title":"Value-aware Quantization for Training and Inference of Neural Networks","date":"2018-04-20","arxiv_id":"1804.07802","n_code_links":0,"syntology":null},{"paper":"/paper/adafactor-adaptive-learning-rates-with","slug":"adafactor-adaptive-learning-rates-with","title":"Adafactor: Adaptive Learning Rates with Sublinear Memory Cost","date":"2018-04-11","arxiv_id":"1804.04235","n_code_links":5,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/human-semantic-parsing-for-person-re","slug":"human-semantic-parsing-for-person-re","title":"Human Semantic Parsing for Person Re-identification","date":"2018-03-31","arxiv_id":"1804.00216","n_code_links":0,"syntology":null},{"paper":"/paper/distributed-prioritized-experience-replay","slug":"distributed-prioritized-experience-replay","title":"Distributed Prioritized Experience Replay","date":"2018-03-02","arxiv_id":"1803.00933","n_code_links":15,"syntology":{"ran":9,"of":15,"n_ran_checked":9,"n_instrument":0,"unverified":6,"pointer_only":3,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","official":null}},{"paper":null,"slug":"classification-of-breast-cancer-histology-1","title":"Classification of breast cancer histology images using transfer learning","date":"2018-02-26","arxiv_id":"1802.09424","n_code_links":0,"syntology":null},{"paper":"/paper/impala-scalable-distributed-deep-rl-with","slug":"impala-scalable-distributed-deep-rl-with","title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","date":"2018-02-05","arxiv_id":"1802.01561","n_code_links":24,"syntology":{"ran":16,"of":34,"n_ran_checked":10,"n_instrument":6,"unverified":18,"pointer_only":3,"phrase":"16 ran (of which 6 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 1 violated, 8 with no contract checked; 6 where Syntology's instrument failed) · 18 unverified","official":{"repos":["deepmind/scalable_agent"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/regularized-evolution-for-image-classifier","slug":"regularized-evolution-for-image-classifier","title":"Regularized Evolution for Image Classifier Architecture Search","date":"2018-02-05","arxiv_id":"1802.01548","n_code_links":5,"syntology":null},{"paper":null,"slug":"handwritten-isolated-bangla-compound","title":"Handwritten Isolated Bangla Compound Character Recognition: a new benchmark using a novel deep learning approach","date":"2018-02-02","arxiv_id":"1802.00671","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-the-robustness-of-neural-networks","slug":"evaluating-the-robustness-of-neural-networks","title":"Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approach","date":"2018-01-31","arxiv_id":"1801.10578","n_code_links":1,"syntology":null},{"paper":"/paper/mobilenetv2-inverted-residuals-and-linear","slug":"mobilenetv2-inverted-residuals-and-linear","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","date":"2018-01-13","arxiv_id":"1801.04381","n_code_links":159,"syntology":{"ran":85,"of":111,"n_ran_checked":65,"n_instrument":20,"unverified":26,"pointer_only":64,"phrase":"85 ran (of which 40 constructed an object rather than computing a result; 65 with no instrument failure: 8 honoured, 0 violated, 57 with no contract checked; 20 where Syntology's instrument failed) · 26 unverified","official":null}},{"paper":null,"slug":"large-scale-3d-scene-classification-with","title":"Large-Scale 3D Scene Classification With Multi-View Volumetric CNN","date":"2017-12-26","arxiv_id":"1712.09216","n_code_links":0,"syntology":null},{"paper":"/paper/improving-generalization-performance-by","slug":"improving-generalization-performance-by","title":"Improving Generalization Performance by Switching from Adam to SGD","date":"2017-12-20","arxiv_id":"1712.07628","n_code_links":6,"syntology":null},{"paper":null,"slug":"towards-practical-verification-of-machine","title":"Towards Practical Verification of Machine Learning: The Case of Computer Vision Systems","date":"2017-12-05","arxiv_id":"1712.01785","n_code_links":0,"syntology":null},{"paper":null,"slug":"vprop-variational-inference-using-rmsprop","title":"Vprop: Variational Inference using RMSprop","date":"2017-12-04","arxiv_id":"1712.01038","n_code_links":0,"syntology":null},{"paper":"/paper/progressive-neural-architecture-search","slug":"progressive-neural-architecture-search","title":"Progressive Neural Architecture Search","date":"2017-12-02","arxiv_id":"1712.00559","n_code_links":18,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["chenxi116/PNASNet.TF","tensorflow/models","chenxi116/PNASNet.pytorch"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"bpgrad-towards-global-optimality-in-deep","title":"BPGrad: Towards Global Optimality in Deep Learning via Branch and Pruning","date":"2017-11-19","arxiv_id":"1711.06959","n_code_links":0,"syntology":null},{"paper":null,"slug":"extremely-large-minibatch-sgd-training-resnet","title":"Extremely Large Minibatch SGD: Training ResNet-50 on ImageNet in 15 Minutes","date":"2017-11-12","arxiv_id":"1711.04325","n_code_links":0,"syntology":null},{"paper":null,"slug":"follow-the-moving-leader-in-deep-learning","title":"Follow the Moving Leader in Deep Learning","date":"2017-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-optimizer-search-using-reinforcement","title":"Neural Optimizer Search using Reinforcement Learning","date":"2017-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/learning-transferable-architectures-for","slug":"learning-transferable-architectures-for","title":"Learning Transferable Architectures for Scalable Image Recognition","date":"2017-07-21","arxiv_id":"1707.07012","n_code_links":17,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":null}},{"paper":"/paper/revisiting-unreasonable-effectiveness-of-data","slug":"revisiting-unreasonable-effectiveness-of-data","title":"Revisiting Unreasonable Effectiveness of Data in Deep Learning Era","date":"2017-07-10","arxiv_id":"1707.02968","n_code_links":2,"syntology":null},{"paper":null,"slug":"variants-of-rmsprop-and-adagrad-with","title":"Variants of RMSProp and Adagrad with Logarithmic Regret Bounds","date":"2017-06-17","arxiv_id":"1706.05507","n_code_links":0,"syntology":null},{"paper":"/paper/yellowfin-and-the-art-of-momentum-tuning","slug":"yellowfin-and-the-art-of-momentum-tuning","title":"YellowFin and the Art of Momentum Tuning","date":"2017-06-12","arxiv_id":"1706.03471","n_code_links":2,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":null}}],"record_sha256":"c6989eb24c302134229bc3d18830bdc0250f52f04e96d8853036412ba1ecb7d3","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}