Catégorie : Notes
-
16 December, 2020 07:57
https://junkiyoshi.com/openframeworks20201213/!~OMSelectionMarkerStart~!!~OMSelectionMarkerEnd~!
-
Making BERT Easier with Preprocessing Models From TensorFlow Hub
BERT and other Transformer encoder architectures have been very successful in natural language processing (NLP) for computing vector-space representations of text, both in advancing the state of the art in academic benchmarks as well as in large-scale applications like Google Search. BERT has been available for TensorFlow since it was created, but originally relied on…
-
Production Machine Learning Monitoring: Outliers, Drift, Explainers & Statistical Performance
A practical deep dive on production monitoring architectures for machine learning at scale using real-time metrics, outlier detectors, drift detectors, metrics servers and explainers. https://towardsdatascience.com/production-machine-learning-monitoring-outliers-drift-explainers-statistical-performance-d9b1d02ac158 Production Machine Learning Monitoring: Outliers, Drift, Explainers & Statistical Performance | by Alejandro Saucedo | Dec, 2020 | Towards Data Science In this article we present an end-to-end example showcasing…
-
GPolS: A Contextual Graph-Based Language Model for Analyzing Parliamentary Debates and Political Cohesion – ACL Anthology
https://www.aclweb.org/anthology/2020.coling-main.426/!~OMSelectionMarkerStart~!!~OMSelectionMarkerEnd~!
-
Best NLP competitions on Kaggle (to learn from) – YouTube
https://m.youtube.com/watch?v=-nH4OSyjwSI!~OMSelectionMarkerStart~!!~OMSelectionMarkerEnd~!
-
11 December, 2020 21:20
https://towardsdatascience.com/classification-regression-and-prediction-whats-the-difference-5423d9efe4ec Classification, regression, and prediction — what’s the difference? | by Cassie Kozyrkov | Dec, 2020 | Towards Data Science The coarsest way to, ahem, classify supervised machine learning (ML) tasks is into classification versus prediction. (What’s supervised ML? See the video below if you need a refresher.) If you’re new… towardsdatascience.com
-
Consistent Video Depth Estimation
https://roxanneluo.github.io/Consistent-Video-Depth-Estimation/ Consistent Video Depth Estimation – GitHub Pages Abstract. We present an algorithm for reconstructing dense, geometrically consistent depth for all pixels in a monocular video. We leverage a conventional structure-from-motion reconstruction to establish geometric constraints on pixels in the video. roxanneluo.github.io
-
Summarization Using Pegasus Model with the Transformers Library | by Chetan Ambi | Towards AI | Nov, 2020 | Medium
https://medium.com/towards-artificial-intelligence/summarization-using-pegasus-model-with-the-transformers-library-553cd0dc5c2!~OMSelectionMarkerStart~!!~OMSelectionMarkerEnd~!
-
Google AI Blog: Using AutoML for Time Series Forecasting
https://ai.googleblog.com/2020/12/using-automl-for-time-series-forecasting.html?m=1!~OMSelectionMarkerStart~!!~OMSelectionMarkerEnd~!
-
Using Genetic Algorithms to Optimize GANs
https://towardsdatascience.com/using-genetic-algorithms-to-optimize-gans-c64e5e02ead4 Using Genetic Algorithms to Optimize GANs | by Victor Sim | Dec, 2020 | Towards Data Science GANs are one of the most computationally intensive models to train, as it is the equivalent of training two neural networks at the same time. For my lousy portable computer, training a GAN until… towardsdatascience.com
-
Deploy Machine Learning Pipeline on AWS Fargate
https://towardsdatascience.com/deploy-machine-learning-pipeline-on-aws-fargate-eb6e1c50507 Deploy Machine Learning Pipeline on AWS Fargate | by Moez Ali | Towards Data Science A step-by-step beginner’s guide to containerize and deploy ML pipeline serverless on AWS Fargate RECAP. In our last post on deploying a machine learning pipeline in the cloud, we demonstrated how to develop a machine learning pipeline in PyCaret,…
-
DevOps on Azure Heat Map
https://azurecharts.com/heatmap?for=devops&_lrsc=f4202f15-6a86-4fa4-ab55-69e312b61134 DevOps on Azure Heat Map Visual summary of Azure updates related to DevOps for last 12 months. azurecharts.com
-
Applied ML in Production
https://madewithml.com/courses/applied-ml-in-production/ Applied ML in Production · Made With ML If are are planning to use this as a guide for applying ML in production, be aware that it takes a lot of effort (initial, maintenance, adaptation) compared to deploying traditional software. The use case should demand large scale experimentation where small improvements provide large business…
-
Speed up your Data Cleaning and Preprocessing with klib
Customized and very easily applicable functions with sensible default values https://towardsdatascience.com/speed-up-your-data-cleaning-and-preprocessing-with-klib-97191d320f80
-
Hover
Hover is a machine teaching library that enables intuitive and effecient supervision. In other words, it provides a map where you hover over and label your data… differently https://github.com/phurwicz/hover phurwicz/hover Human-Oriented Visual ExploRation. Contribute to phurwicz/hover development by creating an account on GitHub. github.com
-
From 0 to 60 (Models) in Two Years: Building Out an Impactful Data Science Function | by Carl Anderson | WW Tech Blog | Dec, 2020 | Medium
https://medium.com/ww-tech-blog/from-0-to-60-models-in-two-years-building-out-an-impactful-data-science-function-9ef86abb9605
-
Discovering your Music Taste with Python and Spotify API
A Step-by-Step Guide to Accessing Spotify Data and Creating a Radar Chart https://towardsdatascience.com/discovering-your-music-taste-with-python-and-spotify-api-b51b0d2744d
-
5 Must-Read Data Science Papers (and How to Use Them) | Towards Data Science
https://towardsdatascience.com/must-read-data-science-papers-487cce9a2020?_branch_match_id=514590978085565439
-
KNN (K-Nearest Neighbors) is Dead!
Long live ANNs for their whopping 380X speedup over sklearn’s KNN while delivering 99.3% similar results. https://medium.com/towards-artificial-intelligence/knn-k-nearest-neighbors-is-dead-fc16507eb3e
-
I created my own YouTube algorithm (to stop me wasting time) | by Chris Lovejoy | Nov, 2020 | Towards Data Science
https://towardsdatascience.com/i-created-my-own-youtube-algorithm-to-stop-me-wasting-time-afd170f4ca3a
-
Average Happiness for Twitter
https://hedonometer.org/timeseries/en_all/ Hedonometer Hedonometer.org is an instrument that measures the happiness of large populations in real time. The hedonometer is based on people’s online expressions, capitalizing on data-rich social media, and measures how people present themselves to the outside world. hedonometer.org https://github.com/andyreagan/hedonometer GitHub – andyreagan/hedonometer: Code running the Hedonometer GitHub is where the world builds software.…
-
PolyFuzz
PolyFuzz performs fuzzy string matching, string grouping, and contains extensive evaluation functions. PolyFuzz is meant to bring fuzzy string matching techniques together within a single framework. Currently, methods include a variety of edit distance measures, a character-based n-gram TF-IDF, word embedding techniques such as FastText and GloVe, and 🤗 transformers embeddings. https://github.com/MaartenGr/PolyFuzz
-
Google and Microsoft Open Sourced These Two Frameworks to Train Deep Learning Models at Scale
GPipe and PipeDream are new frameworks for high scale training in deep learning solutions. https://medium.com/dataseries/google-and-microsoft-open-sourced-these-two-frameworks-to-train-deep-learning-models-at-scale-94d082e6c339 Google and Microsoft Open Sourced These Two Frameworks to Train Deep Learning Models at Scale GPipe and PipeDream are new frameworks for high scale training in deep learning solutions. medium.com
-
ML Infrastructure Tools for Production
https://towardsdatascience.com/ml-infrastructure-tools-for-production-part-2-model-deployment-and-serving-fcfc75c4a362 ML Infrastructure Tools for Production | by Aparna Dhinakaran | Towards Data Science ML Workflow Stages Diagram by Author. Each of these stages of the Machine Learning workflow (Data Preparation, Model Building, and Production) have a number of vertical functions. towardsdatascience.com
-
The Top 5 Machine Learning Algorithms | by Matt Przybyla | Towards Data Science
https://towardsdatascience.com/the-top-5-machine-learning-algorithms-53bc471a2e92
-
Jupyter Best Practices That Will Save You A Lot of Headaches
https://towardsdatascience.com/jupyter-best-practices-that-will-save-you-a-lot-of-headaches-67e1df45e24d Jupyter Best Practices That Will Save You A Lot of Headaches | by Brunna Villar | Nov, 2020 | Towards Data Science H aving been working with Jupyter almost daily for the past three years, I have experienced serious undesired situations that took me back days, or even weeks in my project completion time.…
-
Summarization Using Pegasus Model with the Transformers Library
https://medium.com/towards-artificial-intelligence/summarization-using-pegasus-model-with-the-transformers-library-553cd0dc5c2
-
The Language Interpretability Tool (LIT): Interactive Exploration and Analysis of NLP Models
https://ai.googleblog.com/2020/11/the-language-interpretability-tool-lit.html?m=1 The Language Interpretability Tool (LIT): Interactive Exploration and Analysis of NLP Models Posted by James Wexler, Software Developer and Ian Tenney, Software Engineer, Google Research As natural language processing (NLP) models… ai.googleblog.com
-
GitHub – abhishekkrthakur/tez
https://github.com/abhishekkrthakur/tez
-
Designing ML Orchestration Systems for Startups
https://towardsdatascience.com/designing-ml-orchestration-systems-for-startups-202e527d7897 Designing ML Orchestration Systems for Startups | by Matt Zhou | Oct, 2020 | Towards Data Science Photo by Emile Guillemot on Unsplash. I recently had the chance to build out a machine learning platform at a healthcare startup. This article covers the journey of architecture design, technical tradeoffs, implementation details, and lessons learned…
-
NeoDash – Neo4j Dashboard Builder
https://github.com/nielsdejong/neodash nielsdejong/neodash NeoDash – Neo4j Dashboard Builder. Contribute to nielsdejong/neodash development by creating an account on GitHub. github.com
-
19 November, 2020 20:30
https://github.com/jina-ai/examples/tree/master/cross-modal-search
-
Language Generation with Multi-hop Reasoning on Commonsense Knowledge Graph
https://github.com/cdjhz/multigen GitHub – cdjhz/multigen: Language Generation with Multi-hop Reasoning on Commonsense Knowledge Graph Language Generation with Multi-hop Reasoning on Commonsense Knowledge Graph – cdjhz/multigen github.com
-
15 November, 2020 23:28
https://medium.com/@brunoaziza/2021-predictions-the-end-of-the-dashboard-and-more-e908125d8b8f 2021 Predictions: the end of the dashboard and more… According to Gartner, Data Stories (NOT dashboards) will become the most widespread way of consuming Analytics by 2025, and 75% of these… medium.com
-
GitHub – guillaume-be/rust-bert: Rust native ready-to-use NLP pipelines and transformer-based models (BERT, DistilBERT, GPT2,…)
https://github.com/guillaume-be/rust-bert
-
Self-improving Chatbots based on Deep Reinforcement Learning | by Debmalya Biswas | Towards Data Science
https://towardsdatascience.com/self-improving-chatbots-based-on-reinforcement-learning-75cca62debce
-
Transformers in NLP: Creating a Translator Model from Scratch | Lionbridge AI
https://lionbridge.ai/articles/transformers-in-nlp-creating-a-translator-model-from-scratch/
-
How do Transformers Work? An Introduction | Towards Data Science
https://towardsdatascience.com/how-transformers-work-6cb4629506df
-
Speed Up your AI Code
https://www.brighttalk.com/webcast/18500/454277?utm_source=Element+AI&utm_medium=brighttalk&utm_campaign=454277Christian
-
GitHub – uma-pi1/kge: LibKGE – A knowledge graph embedding library for reproducible research
https://github.com/uma-pi1/kge
-
Comet ❤️ Hugging Face 🤗
https://www.comet.ml/site/comet-hugging-face-integration/ Comet ❤️ Hugging Face 🤗 Get started with auto-logging model metrics and parameters to Comet from the Hugging Face transformers library. www.comet.ml
-
CharBERT: Character-aware Pre-trained Language Model
https://github.com/wtma/CharBERT#charbert-character-aware-pre-trained-language-model https://arxiv.org/abs/2011.01513 https://raw.githubusercontent.com/wtma/CharBERT/main/data/CharBert.png wtma/CharBERT CharBERT: Character-aware Pre-trained Language Model (COLING2020) – wtma/CharBERT github.com
-
11 November, 2020 06:53
https://gevorg-s.medium.com/launching-aim-an-open-ai-development-environment-b0b69d5b8ff2
-
Flutter
https://github.com/flutter/flutter GitHub – flutter/flutter: Flutter makes it easy and fast to build beautiful apps for mobile and beyond. Flutter is Google’s SDK for crafting beautiful, fast user experiences for mobile, web, and desktop from a single codebase. Flutter works with existing code, is used by developers and organizations around the world, and is free and…
-
GitHub – vahidk/EffectivePyTorch: PyTorch tutorials and best practices.
https://github.com/vahidk/EffectivePyTorch
-
Leveraging Pre-trained Language Model Checkpoints for Encoder-Decoder Models
https://huggingface.co/blog/warm-starting-encoder-decoder Leveraging Pre-trained Language Model Checkpoints for Encoder-Decoder Models We’re on a journey to solve and democratize artificial intelligence through natural language. huggingface.co
-
mostlymaths.net | The RDD paper: introducing the Spark general purpose framework
https://mostlymaths.net/2020/11/rdd.html/
-
mostlymaths.net | The RDD paper: introducing the Spark general purpose framework
https://mostlymaths.net/2020/11/rdd.html/