Adversarial NLI: A New Benchmark for Natural Language Understanding
@Machine_learn
Dataset: https://github.com/facebookresearch/anli
Paper: https://arxiv.org/abs/1910.14599
@Machine_learn
Dataset: https://github.com/facebookresearch/anli
Paper: https://arxiv.org/abs/1910.14599
GitHub
GitHub - facebookresearch/anli: Adversarial Natural Language Inference Benchmark
Adversarial Natural Language Inference Benchmark. Contribute to facebookresearch/anli development by creating an account on GitHub.
cicv_22_losch.pdf
4.2 MB
Semantic Bottleneck Layers: Quantifying and Improving Inspectability of Deep Representations
#paper
@Machin_learn
#paper
@Machin_learn
@Machine_learn
8 Top Books on Data Cleaning and Feature Engineering
https://machinelearningmastery.com/books-on-data-cleaning-data-preparation-and-feature-engineering/
8 Top Books on Data Cleaning and Feature Engineering
https://machinelearningmastery.com/books-on-data-cleaning-data-preparation-and-feature-engineering/
Jukebox: a new generative model for audio from OpenAI.
@Machine_learn
openai.com/blog/jukebox
Article: cdn.openai.com/papers/jukebox.pdf
Examples: https://jukebox.openai.com/
Code: https://github.com/openai/jukebox
@Machine_learn
openai.com/blog/jukebox
Article: cdn.openai.com/papers/jukebox.pdf
Examples: https://jukebox.openai.com/
Code: https://github.com/openai/jukebox
Openai
Jukebox
We’re introducing Jukebox, a neural net that generates music, including rudimentary singing, as raw audio in a variety of genres and artist styles. We’re releasing the model weights and code, along with a tool to explore the generated samples.
Building_Machine_Learning_Powered_Applications_Going_From_Idea_to.pdf
9.9 MB
Building Machine Learning Powered Applications
Going from Idea to Product Emmanuel Ameisen
#book #ML
@Machine_learn
Going from Idea to Product Emmanuel Ameisen
#book #ML
@Machine_learn
👍1
Fast and Accurate Neural CRF Constituency Parsing
@Machine_learn
Github: https://github.com/yzhangcs/parser
Paper: https://www.ijcai.org/Proceedings/2020/560
@Machine_learn
Github: https://github.com/yzhangcs/parser
Paper: https://www.ijcai.org/Proceedings/2020/560
This media is not supported in your browser
VIEW IN TELEGRAM
(Re)Discovering Protein Structure and Function Through Language Modeling
@Machine_learn
Blog: https://blog.einstein.ai/provis/
Paper: https://arxiv.org/abs/2006.15222
Code: https://github.com/salesforce/provis
#DL #NLU #proteinmodelling #bio #biolearning #insilico
@Machine_learn
Blog: https://blog.einstein.ai/provis/
Paper: https://arxiv.org/abs/2006.15222
Code: https://github.com/salesforce/provis
#DL #NLU #proteinmodelling #bio #biolearning #insilico
Private prediction methods: A systematic study by Facebook Research
➡️@Machine_learn
https://ai.facebook.com/blog/private-prediction-methods-a-systematic-study/
Github: https://github.com/facebookresearch/private_prediction
Paper: https://arxiv.org/pdf/2007.05089.pdf
@ai_machinelearning_big_data
➡️@Machine_learn
https://ai.facebook.com/blog/private-prediction-methods-a-systematic-study/
Github: https://github.com/facebookresearch/private_prediction
Paper: https://arxiv.org/pdf/2007.05089.pdf
@ai_machinelearning_big_data
Meta
Private prediction methods: A systematic study
The first systematic study of the performance of all main private prediction techniques in realistic machine learning (ML) scenarios. This study is meant to help solve…
Data_Analysis_A_Model_Comparison_Approach_To_Regression,_ANOVA,.pdf
2.1 MB
Data Analysis
A Model Comparison Approach to Regression, ANOVA, and Beyond
Third Edition
#book
@Machine_learn
A Model Comparison Approach to Regression, ANOVA, and Beyond
Third Edition
#book
@Machine_learn
Learning perturbation sets for robust machine learning
➡️@Machine_learn
Git: https://locuslab.github.io/2020-07-20-perturbation/
Code: https://github.com/locuslab/perturbation_learning
Paper: https://arxiv.org/abs/2007.08450
➡️@Machine_learn
Git: https://locuslab.github.io/2020-07-20-perturbation/
Code: https://github.com/locuslab/perturbation_learning
Paper: https://arxiv.org/abs/2007.08450
locuslab.github.io
Learning perturbation sets for robust machine learning
Using generative modeling to capture real-world transformations from data for adversarial robustness
TensorFlow 2.3 is now officially released
@Machine_learn
https://blog.tensorflow.org/2020/07/whats-new-in-tensorflow-2-3.html
@Machine_learn
https://blog.tensorflow.org/2020/07/whats-new-in-tensorflow-2-3.html
blog.tensorflow.org
What's new in TensorFlow 2.3?
TensorFlow 2.3 has been released with new tools to make it easier to load and preprocess data, and solve input-pipeline bottlenecks.