Catégorie : Notes
-
28 January, 2022 07:19
https://medium.com/@anushkhabajpai/mlops-best-resources-340b69615df2
-
JupyterLite
JupyterLite is a JupyterLab distribution that runs entirely in the browser built from the ground-up using JupyterLab components and extensions. https://github.com/jupyterlite/jupyterlite
-
When to Choose CatBoost Over XGBoost or LightGBM Practical Guide
https://neptune.ai/blog/when-to-choose-catboost-over-xgboost-or-lightgbm CatBoost vs XGBoost and LighGBM: When to Choose CatBoost? Boosting algorithms have become one of the most powerful algorithms for training on structural (tabular) data. The three most famous boosting algorithm implementations that have provided various recipes for winning ML competitions are: In this article, we will primarily focus on CatBoost, how it fares…
-
2111.15664 Donut: Document Understanding Transformer without OCR
https://arxiv.org/abs/2111.15664
-
20 January, 2022 13:43
https://towardsdatascience.com/mapie-explained-exactly-how-you-wished-someone-explained-to-you-78fb8ce81ff3
-
Using Deepchecks to Instantly Evaluate ML Models | Towards Data Science
https://towardsdatascience.com/the-newest-package-for-instantly-evaluating-ml-models-deepchecks-d478e1c20d04
-
Hugging Face Tasks
Hugging Face is the home for all Machine Learning tasks. Here you can find what you need to get started with a task: demos, use cases, models, datasets, and more! https://huggingface.co/tasks
-
6 Powerful Feature Engineering Techniques For Time Series Data (using Python)
https://www.analyticsvidhya.com/blog/2019/12/6-powerful-feature-engineering-techniques-time-series/ Feature Engineering Techniques For Time Series Data Feature Engineering for Time Series #2: Time-Based Features. We can similarly extract more granular features if we have the time stamp. For instance, we can determine the hour or minute of the day when the data was recorded and compare the trends between the business hours and…
-
Uber Releases V1.1 of Orbit: A Python Package to Perform Bayesian Time-Series Analysis and Forecasting
https://www.marktechpost.com/2022/01/14/uber-releases-v1-1-of-orbit-a-python-package-to-perform-bayesian-time-series-analysis-and-forecasting/ Uber Releases V1.1 of Orbit: A Python Package to Perform Bayesian Time-Series Analysis and Forecasting – MarkTechPost Last year, the Uber team introduced Orbit, a Bayesian time series modeling user interface which is simple to use, adaptable, interoperable, and high-performing (fast computation). www.marktechpost.com
-
GeLU activation function – On the Impact of the Activation Function on Deep Neural Networks Training
https://arxiv.org/abs/1902.06853 [1902.06853] On the Impact of the Activation Function on Deep Neural Networks Training The weight initialization and the activation function of deep neural networks have a crucial impact on the performance of the training procedure. An inappropriate selection can lead to the loss of information of the input during forward propagation and the exponential…
-
Build Low Code Automated Tensorflow explainable models in just 3 lines of code.
https://github.com/rafiqhasan/auto-tensorflow/
-
10 Takeaways from the Harvard Business Review on Artificial Intelligence
https://medium.com/@walkerinthecloud/10-takeaways-from-the-harvard-business-review-on-artificial-intelligence-9ebbc10c8637 10 Takeaways from the Harvard Business Review on Artificial Intelligence There have been Kondratiev waves throughout history, commonly referred to as innovation waves, including the invention of electricity, the… medium.com
-
Mercury – Easily convert your Python notebooks into interactive web apps
https://github.com/mljar/mercury GitHub – mljar/mercury: Mercury: easily convert Python notebook to web app and share with others Mercury: easily convert Python notebook to web app and share with others – GitHub – mljar/mercury: Mercury: easily convert Python notebook to web app and share with others github.com
-
graviraja/MLOps-Basics
https://github.com/graviraja/MLOps-Basics
-
Optimizing Docker image size and why it matters – contains.dev
https://contains.dev/blog/optimizing-docker-image-size
-
Pyinstrument – a python profiler
https://github.com/joerick/pyinstrument GitHub – joerick/pyinstrument: 🚴 Call stack profiler for Python. Shows you why your code is slow! pyinstrument. Documentation. Pyinstrument is a Python profiler. A profiler is a tool to help you optimize your code – make it faster. To get the biggest speed increase you should focus on the slowest part of your program.Pyinstrument…
-
Implement Your Own Music Recommender with Graph Neural Networks (LightGCN)
https://medium.com/@benalex/implement-your-own-music-recommender-with-graph-neural-networks-lightgcn-f59e3bf5f8f5 Implement Your Own Music Recommender with Graph Neural Networks (LightGCN) By Ben Alexander, Jean-Peic Chou, and Aman Bansal for Stanford CS224W. medium.com
-
yueyu1030/COSINE: This is the code for our paper `Fine-Tuning Pre-trained Language Model with Weak Supervision: A Contrastive-Regularized Self-Training Approach’ (In Proc. of NAACL-HLT 2021).
https://github.com/yueyu1030/COSINE
-
8 Booming Data Science Libraries You Must Watch Out For in 2022
https://towardsdatascience.com/8-booming-data-science-libraries-you-must-watch-out-in-2022-cec2dbb42437
-
NVIDIA is offering a four-hour, self-paced course on MLOps
https://analyticsindiamag.com/nvidia-is-offering-a-four-hour-self-paced-course-on-mlops/
-
Yale University and IBM Researchers Introduce Kernel Graph Neural Networks (KerGNNs) – MarkTechPost
https://www.marktechpost.com/2022/01/07/yale-university-and-ibm-researchers-introduce-kernel-graph-neural-networks-kergnns/
-
Sparsity Without Sacrifice: Accurate BERT with 10x Fewer Parameters
https://medium.com/@Numenta/sparsity-without-sacrifice-accurate-bert-with-10x-fewer-parameters-4206917ddf2f Sparsity Without Sacrifice: Accurate BERT with 10x Fewer Parameters How can we take a step towards the brain’s efficiency without sacrificing accuracy? medium.com
-
RPA for Python
https://github.com/tebelorg/RPA-Python
-
What Are the Prevailing Explainability Methods?
https://towardsdatascience.com/what-are-the-prevailing-explainability-methods-3bc1a44f94df What Are the Prevailing Explainability Methods? | by Aparna Dhinakaran | Dec, 2021 | Towards Data Science The adoption of machine learning (ML) has resulted in an array of artificial intelligence (AI) applications in the growing areas of language processing, computer vision, unsupervised learning and… towardsdatascience.com
-
APPRENTISSAGE PROFOND – DS-GA 1008 – PRINTEMPS 2020 – NYU CENTER FOR DATA SCIENCE
https://atcold.github.io/pytorch-Deep-Learning/fr/ APPRENTISSAGE PROFOND · Apprentissage Profond Description. Ce cours porte sur les techniques de représentation et d’apprentissage profond les plus récentes. Il se concentre sur l’apprentissage supervisé, non supervisé et autosupervisté, mais aussi sur les méthodes d’enchâssement, l’apprentissage métrique et les réseaux convolutifs et récurrents. atcold.github.io
-
3 January, 2022 23:05
https://towardsdatascience.com/machine-learning-in-sql-using-pycaret-87aff377d90c
-
HyperStyle
https://yuval-alaluf.github.io/hyperstyle/
-
3 January, 2022 23:05
https://towardsdatascience.com/neurips-2021-10-papers-you-shouldnt-miss-80f9c0793a3a
-
Practical AI by Ramsri – YouTube
https://m.youtube.com/c/PracticalAIbyRamsri
-
Technique enables real-time rendering of scenes in 3D | MIT News | Massachusetts Institute of Technology
https://news.mit.edu/2021/3-d-image-rendering-1207
-
voila-dashboards/voila: Voil turns Jupyter notebooks into standalone web applications
https://github.com/voila-dashboards/voila
-
The birth of an important discovery in deep clustering | by Giansalvo Cirrincione | Dec, 2021 | Towards Data Science
https://towardsdatascience.com/the-birth-of-an-important-discovery-in-deep-clustering-c2791f2f2d82
-
LePetit: A pre-training efficient and lightning fast French Language Model | by Micheli Vincent | Illuin | Medium
https://medium.com/illuin/lepetit-a-pre-training-efficient-and-lightning-fast-french-language-model-96495ad726b3
-
explosion/spacy-streamlit: 👑 spaCy building blocks and visualizers for Streamlit apps
https://github.com/explosion/spacy-streamlit
-
End-to-End AutoML Pipeline with H2O AutoML, MLflow, FastAPI, and Streamlit | by Kenneth Leung | Dec, 2021 | Towards Data Science
https://towardsdatascience.com/end-to-end-automl-train-and-serve-with-h2o-mlflow-fastapi-and-streamlit-5d36eedfe606
-
Hugging Face Transformers with Keras: Fine-tune a non-English BERT for Named Entity Recognition
https://www.philschmid.de/huggingface-transformers-keras-tf
-
Spacy Course
https://spacy.io/universe/project/spacy-course
-
Microsoft & GitHub on Git-Based CI / CD for Machine Learning & MLOps | Iguazio
https://www.iguazio.com/sessions/git-based-ci-cd-for-machine-learning-mlops/?utm_campaign=LI_LeadAds_CI_CD_OnDemandWebinar4&utm_source=linkedin&utm_medium=paidsocial&li_fat_id=f15c53aa-870b-4744-b589-8a9a2dd03022
-
TencentARC/GFPGAN: GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.
https://github.com/TencentARC/GFPGAN
-
Microsoft Introduces the Next Generation of the Conversational Language Understanding Client Library – MarkTechPost
https://www.marktechpost.com/2021/12/27/microsoft-introduces-the-next-generation-of-the-conversational-language-understanding-client-library/
-
The age of big promises and small results
https://www.fastcompany.com/90708339/were-living-in-an-age-of-big-tech-promises-and-small-results
-
How We Serverlessly Migrated 1.58 Billion Elasticsearch Documents | by Nicholas Ionata | Stream Monkey
https://blog.streammonkey.com/how-we-serverlessly-migrated-1-58-billion-elasticsearch-documents-33ad3d0d7c4f
-
Alternative Feature Selection Methods in Machine Learning – KDnuggets
https://www.kdnuggets.com/2021/12/alternative-feature-selection-methods-machine-learning.html
-
Introduction to Clustering in Python with PyCaret | by Moez Ali | Nov, 2021 | Towards Data Science
https://towardsdatascience.com/introduction-to-clustering-in-python-with-pycaret-5d869b9714a3
-
NorskRegnesentral/skweak: skweak: A software toolkit for weak supervision applied to NLP tasks
https://github.com/NorskRegnesentral/skweak
-
2021 in review: unsupervised brain models
https://xcorr.net/2021/12/31/2021-in-review-unsupervised-brain-models/ 2021 in review: unsupervised brain models – xcorr: comp neuro We’re in a golden age of merging AI and neuroscience. No longer tied to conventional publication venues with year-long turnaround times, our field is moving at record speed. As 2021 draws to a close, I wanted to take some time to zoom out and…
-
NorskRegnesentral/skweak: skweak: A software toolkit for weak supervision applied to NLP tasks
https://github.com/NorskRegnesentral/skweak
-
Open source NLP is fueling a new wave of startups
https://venturebeat-com.cdn.ampproject.org/c/s/venturebeat.com/2021/12/23/open-source-nlp-is-fueling-a-new-wave-of-startups/amp/ Open source NLP is fueling a new wave of startups A growing number of startups are offering open source language models as a service, competing with heavyweights like OpenAI. venturebeat-com.cdn.ampproject.org