Recursive Feature Elimination (RFE) for Feature Selection in Python
https://machinelearningmastery.com/rfe-feature-selection-in-python/
https://machinelearningmastery.com/rfe-feature-selection-in-python/
Point2Mesh in PyTorch
Point2Mesh, a technique for reconstructing a surface mesh from an input point cloud.
https://ranahanocka.github.io/point2mesh/
Github: https://github.com/ranahanocka/point2mesh
Paper: https://arxiv.org/abs/2005.11084
Point2Mesh, a technique for reconstructing a surface mesh from an input point cloud.
https://ranahanocka.github.io/point2mesh/
Github: https://github.com/ranahanocka/point2mesh
Paper: https://arxiv.org/abs/2005.11084
GitHub
GitHub - ranahanocka/point2mesh: Reconstruct Watertight Meshes from Point Clouds [SIGGRAPH 2020]
Reconstruct Watertight Meshes from Point Clouds [SIGGRAPH 2020] - ranahanocka/point2mesh
How to Use Polynomial Feature Transforms for Machine Learning
https://machinelearningmastery.com/polynomial-features-transforms-for-machine-learning/
https://machinelearningmastery.com/polynomial-features-transforms-for-machine-learning/
MachineLearningMastery.com
How to Use Polynomial Feature Transforms for Machine Learning - MachineLearningMastery.com
Often, the input features for a predictive modeling task interact in unexpected and often nonlinear ways. These interactions can be identified and modeled by a learning algorithm. Another approach is to engineer new features that expose these interactions…
GPT-3: Language Models are Few-Shot Learners
Github: https://github.com/openai/gpt-3
Paper: https://arxiv.org/abs/2005.14165v1
Github: https://github.com/openai/gpt-3
Paper: https://arxiv.org/abs/2005.14165v1
GitHub
GitHub - openai/gpt-3: GPT-3: Language Models are Few-Shot Learners
GPT-3: Language Models are Few-Shot Learners. Contribute to openai/gpt-3 development by creating an account on GitHub.
DADS: Unsupervised Reinforcement Learning for Skill Discovery
https://ai.googleblog.com/2020/05/dads-unsupervised-reinforcement.html
https://ai.googleblog.com/2020/05/dads-unsupervised-reinforcement.html
blog.research.google
DADS: Unsupervised Reinforcement Learning for Skill Discovery
Finding Cross-Lingual Syntax in Multilingual BERT
https://ai.stanford.edu/blog/finding-crosslingual-syntax/
https://ai.stanford.edu/blog/finding-crosslingual-syntax/
Eisen
A simple, fast and robust deep learning development framework
https://github.com/eisen-ai/eisen-core
https://eisen-ai.github.io/
A simple, fast and robust deep learning development framework
https://github.com/eisen-ai/eisen-core
https://eisen-ai.github.io/
GitHub
eisen-ai/eisen-core
Core functionality of Eisen. Contribute to eisen-ai/eisen-core development by creating an account on GitHub.
How to Perform Feature Selection With Numerical Input Data - Machine Learning Mastery
https://machinelearningmastery.com/feature-selection-with-numerical-input-data/
https://machinelearningmastery.com/feature-selection-with-numerical-input-data/
MachineLearningMastery.com
How to Perform Feature Selection With Numerical Input Data - MachineLearningMastery.com
Feature selection is the process of identifying and selecting a subset of input features that are most relevant to the target variable. Feature selection is often straightforward when working with real-valued input and output data, such as using the Pearson’s…
MotionNet: Joint Perception and Motion Prediction for Autonomous Driving Based on Bird's Eye View Maps
https://www.catalyzex.com/paper/arxiv:2003.06754
https://www.catalyzex.com/paper/arxiv:2003.06754
How Detectron2 helps make mines safer and more efficient
https://ai.facebook.com/blog/how-detectron2-helps-make-mines-safer-and-more-efficient/
Article: https://medium.com/pytorch/how-datarock-is-using-pytorch-for-more-intelligent-decision-making-d5d1694ba170
https://ai.facebook.com/blog/how-detectron2-helps-make-mines-safer-and-more-efficient/
Article: https://medium.com/pytorch/how-datarock-is-using-pytorch-for-more-intelligent-decision-making-d5d1694ba170
Facebook
How Detectron2 helps make mines safer and more efficient
Datarock, a SaaS solution targeted at the mining industry, leverages various PyTorch tools, including PyTorch-based object detection library Detectron2, to train ML models with geological imagery.
BentoML
BentoML is an open-source platform for high-performance ML model serving.
https://github.com/bentoml/BentoML
bentoml/BentoML
BentoML is an open-source platform for high-performance ML model serving.
https://github.com/bentoml/BentoML
bentoml/BentoML
GitHub
GitHub - bentoml/BentoML: The easiest way to serve AI apps and models - Build Model Inference APIs, Job queues, LLM apps, Multi…
The easiest way to serve AI apps and models - Build Model Inference APIs, Job queues, LLM apps, Multi-model pipelines, and more! - bentoml/BentoML
Nonparametric Feature Impact and Importance
stratx is a library for A Stratification Approach to Partial Dependence for Codependent Variables
Paper: https://arxiv.org/abs/2006.04750v1
Github: https://github.com/parrt/stratx
stratx is a library for A Stratification Approach to Partial Dependence for Codependent Variables
Paper: https://arxiv.org/abs/2006.04750v1
Github: https://github.com/parrt/stratx
GitHub
GitHub - parrt/stratx: stratx is a library for A Stratification Approach to Partial Dependence for Codependent Variables
stratx is a library for A Stratification Approach to Partial Dependence for Codependent Variables - parrt/stratx
Extracting Structured Data from Templatic Documents
https://ai.googleblog.com/2020/06/extracting-structured-data-from.html
https://ai.googleblog.com/2020/06/extracting-structured-data-from.html
MatchGAN: A Self-supervised Semi-supervised Conditional Generative Adversarial Network
Extensive empirical evaluation demonstrates the effectiveness of our proposed method over competitive baselines and existing arts. In particular, our method is able to surpass the baseline with only 20% of the labelled examples used to train the baseline..
Github: https://github.com/justin941208/MatchGAN
Paper: https://arxiv.org/abs/2006.06614v1
Extensive empirical evaluation demonstrates the effectiveness of our proposed method over competitive baselines and existing arts. In particular, our method is able to surpass the baseline with only 20% of the labelled examples used to train the baseline..
Github: https://github.com/justin941208/MatchGAN
Paper: https://arxiv.org/abs/2006.06614v1