![[ICO]](/icons/blank.gif){kind=icon}
![[PARENTDIR]](/icons/back.gif){kind=icon}
![[ ]](/icons/layout.gif){kind=icon}
![[VID]](/icons/movie.gif){kind=icon}
| Name | Last modified | Size | Description |
|---|---|---|---|---|
| Parent Directory | - | ||
| Abadi-2016.pdf | 2016-07-01 00:00 | 2.1M | The Tensorflow project |
| Abramson-2024.pdf | 2024-07-01 00:00 | 8.2M | |
| Anderson-1972.pdf | 1972-07-01 00:00 | 930K | Linear associative memory |
| Arjovsky-2017.pdf | 2017-07-01 00:00 | 8.4M | Wasserstein GAN |
| Bai-2022.pdf | 2022-07-01 00:00 | 2.0M | |
| Barwich-2019.pdf | 2019-07-01 00:00 | 717K | The story of Grandmother cells |
| Bau-2017.pdf | 2017-07-01 00:00 | 3.1M | Network feature dissection |
| Baum-1988.pdf | 1988-07-01 00:00 | 1.6M | Feedforward networks as probability models |
| Becker-1989.pdf | 1989-07-01 00:00 | 1.8M | |
| Bergstra-2010.pdf | 2010-07-01 00:00 | 280K | The Theano project |
| Berlucci-2006.pdf | 2006-07-01 00:00 | 199K | Nobel prize to Hubel and Wiesel |
| Brock-2019.pdf | 2019-07-01 00:00 | 10M | BigGAN |
| Brown-2020.pdf | 2020-07-01 00:00 | 6.5M | |
| Bubek-2023.pdf | 2023-07-01 00:00 | 7.0M | |
| Carlini-2017.pdf | 2017-07-01 00:00 | 1.3M | Evaluating adversarial attacks |
| Carpenter-1991.pdf | 1991-07-01 00:00 | 1.6M | Survey of neural networks in 1991 |
| Chintala-2014.pdf | 2014-07-01 00:00 | 295K | Discussion of Weight Initialization |
| Cho-2014.pdf | 2014-07-01 00:00 | 1.1M | |
| Christiano-2017.pdf | 2017-07-01 00:00 | 3.1M | |
| Collobert-2002.pdf | 2002-07-01 00:00 | 242K | The Torch project |
| Dauphin-2014.pdf | 2014-07-01 00:00 | 1.2M | High dimensional nonconvex losses |
| DeBoer-2003.pdf | 2003-07-01 00:00 | 690K | The cross-entropy sampling method |
| Deng-2009.pdf | 2009-07-01 00:00 | 3.3M | The ImageNet data set |
| Dinh-2017.pdf | 2017-07-01 00:00 | 6.4M | Normalizing Flows, Invertible Neural Networks (INN) |
| Doersch-2021.pdf | 2021-07-01 00:00 | 860K | VAE Tutorial |
| Duchi-2011.pdf | 2011-07-01 00:00 | 301K | The AdaGrad optimizer |
| Erhan-2009.pdf | 2009-07-01 00:00 | 2.0M | |
| Frosst-Hinton-2023.mp4 | 2023-07-01 00:00 | 6.1M | |
| Frostig-2018.pdf | 2018-07-01 00:00 | 619K | |
| Fukushima-1980.pdf | 1980-07-01 00:00 | 1.1M | |
| Glorot-2011.pdf | 2011-07-01 00:00 | 1.0M | Rectified Linear Units |
| Golik-2013.pdf | 2013-07-01 00:00 | 770K | Cross-entropy loss |
| Griewank-1992.pdf | 1992-07-01 00:00 | 1.8M | |
| Griewank-2012.pdf | 2012-07-01 00:00 | 316K | History of autodifferentiation |
| Griewank-2014.pdf | 2014-07-01 00:00 | 301K | |
| Gross-2002.pdf | 2002-07-01 00:00 | 327K | History of the Grandmother Cell story |
| Higgins-2017.pdf | 2017-07-01 00:00 | 33M | Beta-VAE disentangled representations |
| Hinton-1983.pdf | 1983-07-01 00:00 | 654K | Bolzmann machine model of neurons |
| Hinton-1986.pdf | 1986-07-01 00:00 | 4.9M | Distributed representations |
| Hinton-1995.pdf | 1995-07-01 00:00 | 68K | Wake-sleep algorithm |
| Hinton-2006a.pdf | 2006-07-01 00:00 | 618K | Deep belief networks |
| Hinton-2012.pdf | 2012-07-01 00:00 | 1.6M | Dropout preprint |
| Ho-2020.pdf | 2020-07-01 00:00 | 9.8M | Diffusion Models |
| Ho-2022.pdf | 2022-07-01 00:00 | 3.6M | |
| Hoerl-1970.pdf | 1970-07-01 00:00 | 3.2M | Ridge regression, L2 regularization |
| Hopfield-1982.pdf | 1982-07-01 00:00 | 1.2M | Hopfield networks, spin glass model of neurons |
| Hopfield-1987.pdf | 1987-07-01 00:00 | 904K | Feedforward networks as probability models |
| Hornik-1991.pdf | 1991-07-01 00:00 | 1.5M | Universal Approximation |
| HubelWiesel-1962.pdf | 1962-07-01 00:00 | 6.3M | Cat visual cortex, followup paper |
| Hui-2021.pdf | 2021-07-01 00:00 | 821K | Cross-entropy loss |
| Hyvarinen-2009.pdf | 2009-07-01 00:00 | 946K | Topographic independent component analysis |
| Jia-2014.pdf | 2014-07-01 00:00 | 1.4M | The Caffe project |
| Jordan-1986.pdf | 1986-07-01 00:00 | 6.9M | Serial order: recurrent neural networks |
| Jumper-2021.pdf | 2021-07-01 00:00 | 3.5M | |
| Karras-2019.pdf | 2019-07-01 00:00 | 7.1M | StyleGAN |
| Kohonen-1973.pdf | 1973-07-01 00:00 | 384K | Optimal linear associative memory |
| Le-2012.pdf | 2012-07-01 00:00 | 404K | Unsupervised vision from YouTube |
| LeCun-2010.pdf | 2010-07-01 00:00 | 260K | Convolutional network tutorial |
| Lillicrap-2016.pdf | 2016-07-01 00:00 | 648K | Deep Deterministic Policy Gradient |
| Linnainmaa-1976.pdf | 1976-07-01 00:00 | 1.0M | Reverse-mode differentiation |
| Luo-2022.pdf | 2022-07-01 00:00 | 4.8M | |
| Madry-2018.pdf | 2018-07-01 00:00 | 1.2M | Defense against adversarial attack |
| Mikolov-2013a.pdf | 2013-07-01 00:00 | 223K | Word2Vec, Semantic Vector Composition |
| Nair-2010.pdf | 2010-07-01 00:00 | 653K | Rectified Linear Units |
| Nakkiran-2019.pdf | 2019-07-01 00:00 | 8.2M | Deep Double Descent |
| NyTimes-1958.pdf | 1958-07-01 00:00 | 51K | Press account of Rosenblatt |
| OpenAI-2024.pdf | 2024-07-01 00:00 | 4.3M | |
| Papernot-2017.pdf | 2017-07-01 00:00 | 6.5M | Adversarial attacks |
| Paszke-2019.pdf | 2019-07-01 00:00 | 372K | The PyTorch project |
| Piccinini-2004.pdf | 2004-07-01 00:00 | 219K | History of McCulloch-Pitts |
| Polyak-1964.pdf | 1964-07-01 00:00 | 863K | Momentum and classical optimization tricks |
| Radford-2016.pdf | 2016-07-01 00:00 | 7.1M | Deep Convolutional GAN (DCGAN) |
| Radford-2018a.pdf | 2018-07-01 00:00 | 528K | Autoregressive Generative Pretrained Transformer (GPT) |
| Rafailov-2023.pdf | 2023-07-01 00:00 | 908K | |
| Ramesh-2021.pdf | 2021-07-01 00:00 | 9.7M | Text-to-Image Generation (DALL-E) |
| Ramesh-2022.pdf | 2022-07-01 00:00 | 41M | Diffusion model Text-to-Image Generation (DALL-E 2) |
| Ren-2015.pdf | 2015-07-01 00:00 | 744K | Faster R-CNN |
| Rezende-2015.pdf | 2015-07-01 00:00 | 2.8M | |
| Rezende-2016.pdf | 2016-07-01 00:00 | 2.8M | Normalizing Flows, Invertible Neural Networks (INN) |
| Rifai-2011.pdf | 2011-07-01 00:00 | 262K | Contractive Autoencoders |
| Rosenblatt-1958.pdf | 1958-07-01 00:00 | 1.6M | Perceptron Model |
| Rosenblatt-1961.pdf | 1961-07-01 00:00 | 27M | Principles of Neurodynamics Draft |
| Rosenblatt-1962.pdf | 1962-07-01 00:00 | 17M | Perceptron Learning |
| Schuhmann-2022.pdf | 2022-07-01 00:00 | 1.3M | |
| Selvaraju-2016.pdf | 2016-07-01 00:00 | 6.9M | Grad-CAM salience maps |
| Shulman-2017.pdf | 2017-07-01 00:00 | 2.8M | Proximal Policy Optimization (PPO) |
| Spark-Jones-2004.pdf | 2004-07-01 00:00 | 121K | |
| Srivastava-2014.pdf | 2014-07-01 00:00 | 2.7M | Dropout |
| Sundararajan-2017.pdf | 2017-07-01 00:00 | 3.2M | Integrated Gradients salince maps |
| Sutskever-2013.pdf | 2013-07-01 00:00 | 526K | Analysis of Momentum |
| Thoppilan-2022.pdf | 2022-07-01 00:00 | 1.4M | LaMDA Dialog System |
| Tieleman-2012.pdf | 2012-07-01 00:00 | 534K | The RMSProp optimizer |
| Turing-1948.pdf | 1948-07-01 00:00 | 1.8M | Turing's Essay on Intelligent Macinery |
| Turing-1950.pdf | 1950-07-01 00:00 | 484K | Turing's Paper on the Imitation Game |
| Turing-BBC-1951.mp4 | 1951-07-01 00:00 | 30M | |
| VanderOord-2017.pdf | 2017-07-01 00:00 | 3.0M | Vector Quantized VAE (VQ-VAE) |
| Velickovic-2018.pdf | 2018-07-01 00:00 | 1.6M | Graph Attention Networks (GAT) |
| Wei-2022.pdf | 2022-07-01 00:00 | 1.6M | |
| Wei-2022b.pdf | 2024-12-31 14:47 | 871K | |
| Werbos-1981.pdf | 1981-07-01 00:00 | 777K | Backwards methods, an early backpropagation proposal |
| Wurtz-2009.pdf | 2009-07-01 00:00 | 228K | Fifty-year impact of Hubel and Wiesel |
| Xu-2015.pdf | 2015-07-01 00:00 | 3.0M | Show Attend and Tell, Image Captioning |
| Zeiler-2012.pdf | 2012-07-01 00:00 | 524K | |
| Zhang-2019.pdf | 2019-07-01 00:00 | 6.0M | Self-Attention GAN (SAGAN) |
| Zhu-2017.pdf | 2017-07-01 00:00 | 2.6M | CycleGAN unpaired image-to-image |
| Zinkevich-2003.pdf | 2003-07-01 00:00 | 232K | Elegant proof of convergence of SGD |