Pinboard (cshalizi)
https://pinboard.in/u:cshalizi/public/
recent bookmarks from cshalizi[2402.18491] Dynamical Regimes of Diffusion Models2024-03-05T15:29:45+00:00
https://arxiv.org/abs/2402.18491
cshalizito:NB your_favorite_deep_neural_network_sucks of_course_its_really_a_spin_glass neural_networks via:? mezard.marc stochastic_differential_equations mixture_modelshttps://pinboard.in/https://pinboard.in/u:cshalizi/b:c892f4f7dfb6/[2301.02828] Why do Nearest Neighbor Language Models Work?2023-01-13T01:26:13+00:00
https://arxiv.org/abs/2301.02828
cshalizihave_read natural_language_processing neural_networks nearest_neighbors your_favorite_deep_neural_network_sucks large_language_models_(so_called) in_NBhttps://pinboard.in/https://pinboard.in/u:cshalizi/b:3fc0cf7408e6/[2210.05546] What does a deep neural network confidently perceive? The effective dimension of high certainty class manifolds and their low confidence boundaries2022-12-29T02:49:43+00:00
https://arxiv.org/abs/2210.05546
cshalizito:NB adversarial_examples neural_networks your_favorite_deep_neural_network_suckshttps://pinboard.in/https://pinboard.in/u:cshalizi/b:712ef037bf45/Generalization through Memorization: Nearest Neighbor Language Models | OpenReview2022-10-24T01:59:28+00:00
https://openreview.net/forum?id=HklBjCEKvH
cshalizitext_mining natural_language_processing neural_networks nearest_neighbors your_favorite_deep_neural_network_sucks large_language_models_(so_called) in_NBhttps://pinboard.in/https://pinboard.in/u:cshalizi/b:c6e9c942b454/[2208.08489] Understanding Scaling Laws for Recommendation Models2022-09-03T19:30:05+00:00
https://arxiv.org/abs/2208.08489
cshalizirecommender_systems to_teach:data-mining your_favorite_deep_neural_network_sucks in_NBhttps://pinboard.in/https://pinboard.in/u:cshalizi/b:4cf0f6d5f5f3/[2207.08815] Why do tree-based models still outperform deep learning on tabular data?2022-08-25T16:03:35+00:00
https://arxiv.org/abs/2207.08815
cshalizito:NB to_read your_favorite_deep_neural_network_sucks ensemble_methods decision_trees to_teach:data-mininghttps://pinboard.in/https://pinboard.in/u:cshalizi/b:2b5e2a0c03ab/[1906.04493] Generative Adversarial Networks are Special Cases of Artificial Curiosity (1990) and also Closely Related to Predictability Minimization (1991)2022-07-08T13:40:00+00:00
https://arxiv.org/abs/1906.04493
cshalizineural_networks generative_adversarial_networks your_favorite_deep_neural_network_sucks to_teach:data-mininghttps://pinboard.in/https://pinboard.in/u:cshalizi/b:107a922bade3/Moving Beyond Mimicry in Artificial Intelligence - Nautilus | Science Connected2022-07-08T13:35:47+00:00
https://nautil.us/moving-beyond-mimicry-in-artificial-intelligence-21015/
cshalizineural_networks text_mining your_favorite_deep_neural_network_sucks artificial_intelligence via:melanie_mitchell have_read large_language_models_(so_called)https://pinboard.in/https://pinboard.in/u:cshalizi/b:2caf16961f42/The Principles of Deep Learning Theory2022-06-30T17:43:08+00:00
https://www.cambridge.org/core/books/principles-of-deep-learning-theory/3E566F65026D6896DC814A8C31EF3B4C#fndtn-information
cshalizibooks:noted downloaded neural_networks renormalization your_favorite_deep_neural_network_sucks to_read color_me_skeptical in_NBhttps://pinboard.in/https://pinboard.in/u:cshalizi/b:8d138b2c4938/Can Deep Convolutional Neural Networks Learn Same-Different Relations? | bioRxiv2022-06-28T14:10:17+00:00
https://www.biorxiv.org/content/10.1101/2021.04.06.438551v1.abstract
cshalizineural_networks relational_learning your_favorite_deep_neural_network_sucks in_NBhttps://pinboard.in/https://pinboard.in/u:cshalizi/b:b0df8afde152/[2206.04301] Unveiling Transformers with LEGO: a synthetic reasoning task2022-06-13T16:59:20+00:00
https://arxiv.org/abs/2206.04301
cshalizineural_networks artificial_intelligence your_favorite_deep_neural_network_sucks text_mining large_language_models_(so_called) in_NB to_readhttps://pinboard.in/https://pinboard.in/u:cshalizi/b:e20f76c0ad42/[2205.10320] Nothing makes sense in deep learning, except in the light of evolution2022-06-13T16:56:55+00:00
https://arxiv.org/abs/2205.10320
cshalizineural_networks evo-devo your_favorite_deep_neural_network_sucks via:mraginsky in_NBhttps://pinboard.in/https://pinboard.in/u:cshalizi/b:82f6f94e54fc/Playing Games with Ais: The Limits of GPT-3 and Similar Large Language Models | SpringerLink2022-05-27T15:21:27+00:00
https://link.springer.com/article/10.1007/s11023-022-09602-0
cshalizitext_mining neural_networks your_favorite_deep_neural_network_sucks artificial_intelligence philip_k_dick_and_the_fake_humans_rules_everything_around_me in_NB large_language_models_(so_called)https://pinboard.in/https://pinboard.in/u:cshalizi/b:0378888d889b/[2103.14108] The Geometry of Over-parameterized Regression and Adversarial Perturbations2022-05-10T13:13:10+00:00
https://arxiv.org/abs/2103.14108
cshalizito:NB linear_regression neural_networks learning_theory your_favorite_deep_neural_network_sucks via:rvenkat adversarial_exampleshttps://pinboard.in/https://pinboard.in/u:cshalizi/b:af2e2e202d0c/Understanding Deep Learning with Statistical Relevance | Philosophy of Science | Cambridge Core2022-02-15T15:49:49+00:00
https://www.cambridge.org/core/journals/philosophy-of-science/article/understanding-deep-learning-with-statistical-relevance/07B47A16041115D1A84C34220B515831
cshalizito_read information_bottleneck sufficiency neural_networks your_favorite_deep_neural_network_sucks statistical_relevance in_NBhttps://pinboard.in/https://pinboard.in/u:cshalizi/b:2ae97d49f2dd/[2103.14723] Lower Bounds on the Generalization Error of Nonlinear Learning Models2022-01-28T14:52:44+00:00
https://arxiv.org/abs/2103.14723
cshalizito:NB learning_theory neural_networks your_favorite_deep_neural_network_sucks via:mraginsky zeitouni.oferhttps://pinboard.in/https://pinboard.in/u:cshalizi/b:8cc65b86660e/[2003.08907] Overinterpretation reveals image classification model pathologies2021-12-22T18:10:28+00:00
https://arxiv.org/abs/2003.08907
cshaliziclassifiers your_favorite_deep_neural_network_sucks via:? adversarial_examples have_skimmed in_NB have_readhttps://pinboard.in/https://pinboard.in/u:cshalizi/b:628357aee15e/Has AI found a new Foundation?2021-12-13T06:47:27+00:00
https://thegradient.pub/has-ai-found-a-new-foundation/
cshaliziartificial_intelligence marcus.gary your_favorite_deep_neural_network_sucks have_read to:blog large_language_models_(so_called)https://pinboard.in/https://pinboard.in/u:cshalizi/b:1d9f8500741f/[2111.04204v1] Natural Adversarial Objects2021-12-13T06:15:35+00:00
https://arxiv.org/abs/2111.04204
cshalizito:NB to_read adversarial_examples your_favorite_deep_neural_network_suckshttps://pinboard.in/https://pinboard.in/u:cshalizi/b:bdbad3cb8e96/[2107.08590] EvilModel: Hiding Malware Inside of Neural Network Models2021-07-30T13:44:49+00:00
https://arxiv.org/abs/2107.08590
cshaliziyour_favorite_deep_neural_network_sucks via:slanielhttps://pinboard.in/https://pinboard.in/u:cshalizi/b:b475c728e2ad/Understanding adversarial examples requires a theory of artefacts for deep learning | Nature Machine Intelligence2021-07-03T16:51:50+00:00
https://www.nature.com/articles/s42256-020-00266-y
cshalizito:NB adversarial_examples your_favorite_deep_neural_network_sucks statisticshttps://pinboard.in/https://pinboard.in/u:cshalizi/b:8306129e1df0/[1712.02950] CycleGAN, a Master of Steganography2021-06-13T04:20:00+00:00
https://arxiv.org/abs/1712.02950
cshalizito:NB adversarial_examples your_favorite_deep_neural_network_suckshttps://pinboard.in/https://pinboard.in/u:cshalizi/b:68f5dab5132a/[2106.03007] Unbiased Self-Play2021-06-09T02:50:48+00:00
https://arxiv.org/abs/2106.03007
cshalizito:NB reinforcement_learning learning_in_games your_favorite_deep_neural_network_sucks re:in_soviet_union_optimization_problem_solves_youhttps://pinboard.in/https://pinboard.in/u:cshalizi/b:9e0fa81f66b7/[2105.13010] An error analysis of generative adversarial networks for learning distributions2021-06-07T03:58:50+00:00
https://arxiv.org/abs/2105.13010
cshalizito:NB density_estimation your_favorite_deep_neural_network_sucks statisticshttps://pinboard.in/https://pinboard.in/u:cshalizi/b:1e57947289bd/Deep learning in science | Pattern recognition and machine learning | Cambridge University Press2021-05-28T16:34:18+00:00
https://www.cambridge.org/9781108845359
cshalizibooks:noted neural_networks data_mining statistics baldi.pierre your_favorite_deep_neural_network_sucks books:have_suggested_to_library books:in_library downloaded in_NBhttps://pinboard.in/https://pinboard.in/u:cshalizi/b:5f32ee3469e2/Moving beyond “algorithmic bias is a data problem”: Patterns2021-04-29T14:10:08+00:00
https://doi.org/10.1016/j.patter.2021.100241
cshalizihave_read algorithmic_fairness heavy_tails neural_networks your_favorite_deep_neural_network_sucks in_NB tracked_down_references re:codename:one_law_for_the_lion_and_ox_is_oppressionhttps://pinboard.in/https://pinboard.in/u:cshalizi/b:b9d4fd339451/[2104.10601] Statistical inference for generative adversarial networks2021-04-22T15:20:39+00:00
https://arxiv.org/abs/2104.10601
cshalizineural_networks confidence_sets nonparametrics your_favorite_deep_neural_network_sucks in_NBhttps://pinboard.in/https://pinboard.in/u:cshalizi/b:6f7375fd36ee/[2102.08530] Fast Graph Learning with Unique Optimal Solutions2021-04-21T17:59:10+00:00
https://arxiv.org/abs/2102.08530
cshalizito:NB network_data_analysis your_favorite_deep_neural_network_sucks galstyan.aram ver_steeg.greg have_skimmed computational_statisticshttps://pinboard.in/https://pinboard.in/u:cshalizi/b:1e1dc2e388ec/[2104.05508] Noether: The More Things Change, the More Stay the Same2021-04-14T17:04:58+00:00
https://arxiv.org/abs/2104.05508
cshalizito:NB neural_networks optimization symmetry noethers_theorem your_favorite_deep_neural_network_sucks via:mraginskyhttps://pinboard.in/https://pinboard.in/u:cshalizi/b:022615f44720/[2103.09177] Deep learning: a statistical viewpoint2021-03-30T12:16:20+00:00
https://arxiv.org/abs/2103.09177
cshalizilearning_theory neural_networks your_favorite_deep_neural_network_sucks double_descent bartlett.peter_l. montanari.andrea rakhlin.sasha via:rvenkat to_teach:childs_garden_of_statistical_learning_theory in_NB interpolation_aka_memorizing_the_training_datahttps://pinboard.in/https://pinboard.in/u:cshalizi/b:c6986686debf/The Myth of Artificial Intelligence — Erik J. Larson | Harvard University Press2021-03-24T22:10:55+00:00
https://www.hup.harvard.edu/catalog.php?isbn=9780674983519
cshalizito:NB books:noted artificial_intelligence debunking your_favorite_deep_neural_network_sucks re:ai_is_the_technology_of_the_future_and_always_will_be color_me_skeptical books:suggest_to_libraryhttps://pinboard.in/https://pinboard.in/u:cshalizi/b:0c1167eb4f2b/[2101.06887] Can a Fruit Fly Learn Word Embeddings?2021-01-22T05:38:19+00:00
https://arxiv.org/abs/2101.06887
cshalizito:NB text_mining neural_networks natural_language_processing your_favorite_deep_neural_network_suckshttps://pinboard.in/https://pinboard.in/u:cshalizi/b:dab541e23f6b/[2006.04331] Randomized Policy Learning for Continuous State and Action MDPs2021-01-15T21:02:18+00:00
https://arxiv.org/abs/2006.04331
cshalizireinforcement_learning your_favorite_deep_neural_network_sucks random_features have_read in_NB re:codename:catherine_wheelhttps://pinboard.in/https://pinboard.in/u:cshalizi/b:0020868c151c/Finite Time Guarantees for Continuous State MDPs with Generative Model - IEEE Conference Publication2021-01-15T20:49:19+00:00
https://ieeexplore.ieee.org/abstract/document/9303840
cshalizireinforcement_learning simulation-based_inference your_favorite_deep_neural_network_sucks random_features in_NB re:codename:catherine_wheelhttps://pinboard.in/https://pinboard.in/u:cshalizi/b:ff4996593c41/[2012.15180] Out of Order: How important is the sequential order of words in a sentence in Natural Language Understanding tasks?2021-01-14T18:32:51+00:00
https://arxiv.org/abs/2012.15180
cshalizito:NB natural_language_processing your_favorite_deep_neural_network_suckshttps://pinboard.in/https://pinboard.in/u:cshalizi/b:8020347b982d/[2012.07805] Extracting Training Data from Large Language Models2020-12-17T02:04:26+00:00
https://arxiv.org/abs/2012.07805
cshalizijudging the quick and the dead basilisk-dom being amenable to bargaining under the canons of timeless decision theory.]]>have_read your_favorite_deep_neural_network_sucks natural_language_processing text_mining neural_networks privacy large_language_models_(so_called) in_NBhttps://pinboard.in/https://pinboard.in/u:cshalizi/b:c6eb365e40be/[2012.00152] Every Model Learned by Gradient Descent Is Approximately a Kernel Machine2020-12-11T21:54:53+00:00
https://arxiv.org/abs/2012.00152
cshalizito:NB neural_networks optimization domingos.pedro kernel_methods your_favorite_deep_neural_network_sucks i_want_to_believe have_read to_teach:childs_garden_of_statistical_learning_theoryhttps://pinboard.in/https://pinboard.in/u:cshalizi/b:1df171804450/[1906.05301] Learning Curves for Deep Neural Networks: A Gaussian Field Theory Perspective2020-11-30T04:03:21+00:00
https://arxiv.org/abs/1906.05301
cshalizito:NB neural_networks stochastic_processes your_favorite_deep_neural_network_suckshttps://pinboard.in/https://pinboard.in/u:cshalizi/b:7a2336239bf8/Shortcuts: How Neural Networks Love to Cheat2020-11-27T06:05:28+00:00
https://thegradient.pub/shortcuts-neural-networks-love-to-cheat/
cshalizito_teach:data-mining neural_networks machine_learning your_favorite_deep_neural_network_suckshttps://pinboard.in/https://pinboard.in/u:cshalizi/b:56834c587049/Critically Examining the "Neural Hype" | Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval2020-11-27T05:16:26+00:00
https://dl.acm.org/doi/abs/10.1145/3331184.3331340
cshalizito:NB information_retrieval neural_networks your_favorite_deep_neural_network_suckshttps://pinboard.in/https://pinboard.in/u:cshalizi/b:81c9d8582e62/Statistical Mechanics of Deep Learning | Annual Review of Condensed Matter Physics2020-11-19T05:24:54+00:00
https://www.annualreviews.org/doi/abs/10.1146/annurev-conmatphys-031119-050745
cshalizito:NB learning_theory neural_networks your_favorite_deep_neural_network_sucks statistical_mechanicshttps://pinboard.in/https://pinboard.in/u:cshalizi/b:b7fe13bba8f5/Biau , Cadre , Sangnier , Tanielian : Some theoretical properties of GANS2020-11-18T21:50:42+00:00
https://projecteuclid.org/euclid.aos/1594972829
cshalizito:NB statistics estimation your_favorite_deep_neural_network_suckshttps://pinboard.in/https://pinboard.in/u:cshalizi/b:c35ca832e623/Deconstructing Generative Adversarial Networks - IEEE Journals & Magazine2020-11-16T16:10:49+00:00
https://ieeexplore.ieee.org/document/9049093
cshalizito:NB machine_learning generative_adversarial_networks statistics your_favorite_deep_neural_network_suckshttps://pinboard.in/https://pinboard.in/u:cshalizi/b:3c48a2f86a93/[2010.13993] Combining Label Propagation and Simple Models Out-performs Graph Neural Networks2020-11-08T08:47:34+00:00
https://arxiv.org/abs/2010.13993
cshalizinetwork_data_analysis prediction classifiers smoothing your_favorite_deep_neural_network_sucks have_read to_teach:baby-nets in_NBhttps://pinboard.in/https://pinboard.in/u:cshalizi/b:7e9c5fb62793/[2010.15581] The De-democratization of AI: Deep Learning and the Compute Divide in Artificial Intelligence Research2020-10-30T17:51:35+00:00
https://arxiv.org/abs/2010.15581
cshalizito:NB to_read neural_networks your_favorite_deep_neural_network_sucks market_failures_in_everything text_mining causal_inferencehttps://pinboard.in/https://pinboard.in/u:cshalizi/b:21fbbbbcf40b/[2003.08505] A Metric Learning Reality Check2020-08-08T15:01:06+00:00
https://arxiv.org/abs/2003.08505
cshalizito:NB inference_to_latent_objects metric_learning neural_networks your_favorite_deep_neural_network_sucks via:?https://pinboard.in/https://pinboard.in/u:cshalizi/b:0d7f83fb7fc4/[2008.02217] Hopfield Networks is All You Need2020-08-08T15:00:34+00:00
https://arxiv.org/abs/2008.02217
cshalizineural_networks everything_old_is_new_again your_favorite_deep_neural_network_sucks via:? large_language_models_(so_called) in_NB have_readhttps://pinboard.in/https://pinboard.in/u:cshalizi/b:d2b09f062a6e/Eye-catching advances in some AI fields are not real | Science | AAAS2020-07-13T18:13:11+00:00
https://www.sciencemag.org/news/2020/05/eye-catching-advances-some-ai-fields-are-not-real
cshalizitrack_down_references neural_networks your_favorite_deep_neural_network_suckshttps://pinboard.in/https://pinboard.in/u:cshalizi/b:0d50f3390681/Autopsy of a deep learning paper – Piekniewski's blog2020-07-13T17:58:44+00:00
https://blog.piekniewski.info/2018/07/14/autopsy-dl-paper/
cshalizineural_networks classifiers your_favorite_deep_neural_network_suckshttps://pinboard.in/https://pinboard.in/u:cshalizi/b:12413aefa499/Deep Learning: The Good, the Bad, and the Ugly | Annual Review of Vision Science2020-06-26T14:24:52+00:00
https://www.annualreviews.org/doi/10.1146/annurev-vision-091718-014951
cshalizito:NB to_read cognitive_science neural_networks via:rvenkat your_favorite_deep_neural_network_suckshttps://pinboard.in/https://pinboard.in/u:cshalizi/b:773a2e1b079f/On the information bottleneck theory of deep learning - IOPscience2020-04-17T15:42:26+00:00
https://iopscience.iop.org/article/10.1088/1742-5468/ab3985
cshalizineural_networks your_favorite_deep_neural_network_sucks information_bottleneck via:dedeo have_read in_NBhttps://pinboard.in/https://pinboard.in/u:cshalizi/b:52f62818d04b/[2004.07780] Shortcut Learning in Deep Neural Networks2020-04-17T15:40:48+00:00
https://arxiv.org/abs/2004.07780
cshalizito:NB to_read heuristics your_favorite_deep_neural_network_sucks via:dedeohttps://pinboard.in/https://pinboard.in/u:cshalizi/b:c0e7e18f3b03/[1912.03925] Over-parametrized deep neural networks do not generalize well2020-01-12T22:28:23+00:00
https://arxiv.org/abs/1912.03925
cshalizineural_networks regression statistics learning_theory your_favorite_deep_neural_network_sucks to_teach:childs_garden_of_statistical_learning_theory in_NB interpolation_aka_memorizing_the_training_datahttps://pinboard.in/https://pinboard.in/u:cshalizi/b:2c940fef503e/[1910.11626] Seeing What a GAN Cannot Generate2019-10-29T14:10:43+00:00
https://arxiv.org/abs/1910.11626
cshalizito:NB neural_networks your_favorite_deep_neural_network_suckshttps://pinboard.in/https://pinboard.in/u:cshalizi/b:555e7770032f/[1910.07663] Probabilistic Deterministic Finite Automata and Recurrent Networks, Revisited2019-10-19T00:13:19+00:00
https://arxiv.org/abs/1910.07663
cshalizito:NB prediction time_series crutchfield.james_p. your_favorite_deep_neural_network_suckshttps://pinboard.in/https://pinboard.in/u:cshalizi/b:7878ee6e0dc2/[1907.04670] Comparing the Performance of the LSTM and HMM Language Models via Structural Similarity2019-10-17T14:13:01+00:00
https://arxiv.org/abs/1907.04670
cshalizito:NB natural_language_processing text_mining markov_models neural_networks statistics your_favorite_deep_neural_network_suckshttps://pinboard.in/https://pinboard.in/u:cshalizi/b:e02f8d1668fc/[1910.06943] The Local Elasticity of Neural Networks2019-10-16T15:51:32+00:00
https://arxiv.org/abs/1910.06943
cshaliziadversarial_examples neural_networks your_favorite_deep_neural_network_sucks clustering statistics in_NBhttps://pinboard.in/https://pinboard.in/u:cshalizi/b:cc210569d434/[1910.05992] Pathological spectra of the Fisher information metric and its variants in deep neural networks2019-10-15T18:03:28+00:00
https://arxiv.org/abs/1910.05992
cshalizito:NB neural_networks fisher_information your_favorite_deep_neural_network_sucks information_geometry amari.shun-ichihttps://pinboard.in/https://pinboard.in/u:cshalizi/b:88590d05647e/[1910.00164] Entropy Penalty: Towards Generalization Beyond the IID Assumption2019-10-02T15:53:57+00:00
https://arxiv.org/abs/1910.00164
cshaliziinformation_bottleneck adversarial_examples your_favorite_deep_neural_network_sucks in_NB color_me_skepticalhttps://pinboard.in/https://pinboard.in/u:cshalizi/b:ae019fbd1c8b/[1910.00189] The Non-IID Data Quagmire of Decentralized Machine Learning2019-10-02T15:27:14+00:00
https://arxiv.org/abs/1910.00189
cshalizito:NB distributed_systems statistics your_favorite_deep_neural_network_sucks to_readhttps://pinboard.in/https://pinboard.in/u:cshalizi/b:4b83ff8377df/[1910.00359] Truth or Backpropaganda? An Empirical Investigation of Deep Learning Theory2019-10-02T15:21:59+00:00
https://arxiv.org/abs/1910.00359
cshalizineural_networks your_favorite_deep_neural_network_sucks in_NB have_readhttps://pinboard.in/https://pinboard.in/u:cshalizi/b:6a56ae587d08/[1905.01067] Deconstructing Lottery Tickets: Zeros, Signs, and the Supermask2019-10-01T17:32:54+00:00
https://arxiv.org/abs/1905.01067
cshalizito:NB learning_theory neural_networks your_favorite_deep_neural_network_suckshttps://pinboard.in/https://pinboard.in/u:cshalizi/b:208627094568/[1909.12638] On the Anomalous Generalization of GANs2019-10-01T16:45:16+00:00
https://arxiv.org/abs/1909.12638
cshalizito:NB learning_theory your_favorite_deep_neural_network_suckshttps://pinboard.in/https://pinboard.in/u:cshalizi/b:393623029bf2/[1905.11926] Network Deconvolution2019-10-01T16:39:15+00:00
https://arxiv.org/abs/1905.11926
cshalizito:NB neural_networks statistics principal_components karl_pearson_died_for_your_sins your_favorite_deep_neural_network_sucks to_readhttps://pinboard.in/https://pinboard.in/u:cshalizi/b:6d139c0cc67c/[1811.02549] Language GANs Falling Short2019-08-20T14:24:45+00:00
https://arxiv.org/abs/1811.02549
cshalizito:NB natural_language_processing model_checking your_favorite_deep_neural_network_sucks to_readhttps://pinboard.in/https://pinboard.in/u:cshalizi/b:47fb28f5b9fd/[1907.06902] Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approaches2019-07-30T18:01:31+00:00
https://arxiv.org/abs/1907.06902
cshaliziinformation_retrieval your_favorite_deep_neural_network_sucks in_NB collaborative_filtering recommender_systemshttps://pinboard.in/https://pinboard.in/u:cshalizi/b:19e4d07b80cb/[1905.11382] State-Reification Networks: Improving Generalization by Modeling the Distribution of Hidden Representations2019-05-29T21:12:04+00:00
https://arxiv.org/abs/1905.11382
cshalizito:NB to_read neural_networks learning_theory your_favorite_deep_neural_network_sucks adversarial_exampleshttps://pinboard.in/https://pinboard.in/u:cshalizi/b:24ca758d5dcf/[1905.10409] Greedy Shallow Networks: A New Approach for Constructing and Training Neural Networks2019-05-28T17:40:53+00:00
https://arxiv.org/abs/1905.10409
cshalizito:NB learning_theory approximation neural_networks your_favorite_deep_neural_network_suckshttps://pinboard.in/https://pinboard.in/u:cshalizi/b:99b556b19030/[1905.10854] All Neural Networks are Created Equal2019-05-28T17:23:06+00:00
https://arxiv.org/abs/1905.10854
cshalizito:NB to_read optimization machine_learning neural_networks your_favorite_deep_neural_network_suckshttps://pinboard.in/https://pinboard.in/u:cshalizi/b:c0c78ad85e3f/[1905.10887] Classification Accuracy Score for Conditional Generative Models2019-05-28T17:05:33+00:00
https://arxiv.org/abs/1905.10887
cshalizito:NB machine_learning your_favorite_deep_neural_network_suckshttps://pinboard.in/https://pinboard.in/u:cshalizi/b:b6a85bd82b2a/