Exploring Low Rank Training of Deep Neural Networks von Kamalakara, Siddhartha Rao, Locatelli, Acyr, Venkitesh, Bharat, Ba, Jimmy, Gal, Yarin, Gomez, Aidan N

Volltext bestellen

Improving compute efficacy frontiers with SliceOut von Notin, Pascal, Gomez, Aidan N, Yoo, Joanna, Gal, Yarin

Volltext bestellen

Wat zei je? Detecting Out-of-Distribution Translations with Variational Transformers von Xiao, Tim Z, Gomez, Aidan N, Gal, Yarin

Volltext bestellen

Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning von Kossen, Jannik, Band, Neil, Lyle, Clare, Gomez, Aidan N, Rainforth, Tom, Gal, Yarin

Volltext bestellen

Robustness to Pruning Predicts Generalization in Deep Neural Networks von Kuhn, Lorenz, Lyle, Clare, Gomez, Aidan N, Rothfuss, Jonas, Gal, Yarin

Volltext bestellen

Depthwise Separable Convolutions for Neural Machine Translation von Kaiser, Lukasz, Gomez, Aidan N, Chollet, Francois

Volltext bestellen

Interlocking Backpropagation: Improving depthwise model-parallelism von Gomez, Aidan N, Key, Oscar, Perlin, Kuba, Gou, Stephen, Frosst, Nick, Dean, Jeff, Gal, Yarin

Volltext bestellen

Prioritized Training on Points that are Learnable, Worth Learning, and Not Yet Learnt von Mindermann, Sören, Brauner, Jan, Razzak, Muhammed, Sharma, Mrinank, Kirsch, Andreas, Xu, Winnie, Höltgen, Benedikt, Gomez, Aidan N, Morisot, Adrien, Farquhar, Sebastian, Gal, Yarin

Volltext bestellen

Prioritized training on points that are learnable, worth learning, and not yet learned (workshop version) von Mindermann, Sören, Razzak, Muhammed, Xu, Winnie, Kirsch, Andreas, Sharma, Mrinank, Morisot, Adrien, Gomez, Aidan N, Farquhar, Sebastian, Brauner, Jan, Gal, Yarin

Volltext bestellen

System and method for low rank training of neural networks von Aidan N. Gomez, Siddhartha Rao Kamalakara, Bharat Venkitesh, Acyr Flavio Neto Locatelli

Volltext bestellen

The Reversible Residual Network: Backpropagation Without Storing Activations von Gomez, Aidan N, Ren, Mengye, Urtasun, Raquel, Grosse, Roger B

Volltext bestellen

System and Method for Low Rank Training of Neural Networks von GOMEZ, Aidan N, KAMALAKARA, Siddhartha Rao, Locatelli, Acyr Flavio Neto, VENKITESH, Bharat

Volltext bestellen

SYSTEM AND METHOD FOR LOW RANK TRAINING OF NEURAL NETWORKS von VENKITESH, BHARAT, LOCATELLI, ACYR FLAVIO NETO, KAMALAKARA, SIDDHARTHA RAO, GOMEZ, AIDAN N

Volltext bestellen

Improving compute efficacy frontiers with SliceOut von Notin, Pascal, Gomez, Aidan N, Yoo, Joanna, Yarin Gal

Volltext

Exploring Low Rank Training of Deep Neural Networks von Siddhartha Rao Kamalakara, Locatelli, Acyr, Venkitesh, Bharat, Ba, Jimmy, Yarin Gal, Gomez, Aidan N

Volltext

Attention Is All You Need von Vaswani, Ashish, Shazeer, Noam, Parmar, Niki, Uszkoreit, Jakob, Jones, Llion, Gomez, Aidan N, Kaiser, Lukasz, Polosukhin, Illia

Volltext

Learning Sparse Networks Using Targeted Dropout von Gomez, Aidan N, Zhang, Ivan, Kamalakara, Siddhartha Rao, Madaan, Divyam, Swersky, Kevin, Gal, Yarin, Hinton, Geoffrey E

Volltext bestellen

Interlocking Backpropagation: Improving depthwise model-parallelism von Gomez, Aidan N, Key, Oscar, Perlin, Kuba, Gou, Stephen, Frosst, Nick, Dean, Jeff, Yarin Gal

Volltext

Wat zei je? Detecting Out-of-Distribution Translations with Variational Transformers von Xiao, Tim Z, Gomez, Aidan N, Yarin Gal

Volltext

A Systematic Comparison of Bayesian Deep Learning Robustness in Diabetic Retinopathy Tasks von Filos, Angelos, Farquhar, Sebastian, Gomez, Aidan N, Rudner, Tim G. J, Kenton, Zachary, Smith, Lewis, Alizadeh, Milad, de Kroon, Arnoud, Gal, Yarin

Volltext bestellen