Catégorie : Notes
-
14 September, 2021 07:25
https://towardsdatascience.com/image-segmentation-with-clustering-b4bbc98f2ee6
-
13 September, 2021 15:32
https://techno-sapien.com/blog/seven-data-science-mistakes Seven Mistakes You’re Making As You Build a Data Science Team — Techno Sapien The common thread of effective data science is leadership, culture and collaboration. techno-sapien.com
-
Online materials for Social Data Science
https://dgarcia-eu.github.io/SocialDataScience/ Social Data Science | Online materials for Social Data Science Social Data Science. David Garcia, 2021. Welcome to the online materials for Social Data Science. Social Data Science is an emerging field that studies human behavior and social interaction through digital traces. dgarcia-eu.github.io
-
FLAML – Fast and Lightweight AutoML
https://github.com/microsoft/FLAML GitHub – microsoft/FLAML: A fast and lightweight AutoML library. Advantages. For common machine learning tasks like classification and regression, find quality models with small computational resources. Users can choose their desired customizability: minimal customization (computational resource budget), medium customization (e.g., scikit-style learner, search space and metric), full customization (arbitrary training and evaluation code). github.com
-
The Machine & Deep Learning Compendium
https://github.com/orico/www.mlcompendium.com/
-
2109.00725 Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond
https://arxiv.org/abs/2109.00725
-
How Commonsense Knowledge Helps with Natural Language Tasks: A Survey of Recent Resources and Methodologies
https://arxiv.org/abs/2108.04674 [2108.04674] How Commonsense Knowledge Helps with Natural Language Tasks: A Survey of Recent Resources and Methodologies In this paper, we give an overview of commonsense reasoning in natural language processing, which requires a deeper understanding of the contexts and usually involves inference over implicit external knowledge. We first review some popular commonsense knowledge bases…
-
GitHub – Yale-LILY/SummerTime: An open-source text summarization toolkit for non-experts.
https://github.com/Yale-LILY/SummerTime
-
UCSD & Microsoft Improve Image Recognition With Extremely Low FLOPs | Synced
https://syncedreview.com/2021/08/23/deepmind-podracer-tpu-based-rl-frameworks-deliver-exceptional-performance-at-low-cost-88/
-
Centroid Neural Network: An Efficient and Stable Clustering Algorithm
https://pub.towardsai.net/centroid-neural-network-an-efficient-and-stable-clustering-algorithm-b2fa8cbb2a27 Centroid Neural Network: An Efficient and Stable Clustering Algorithm Let’s upraise potentials that are not paid much attention pub.towardsai.net
-
What Have Language Models Learned?
https://pair.withgoogle.com/explorables/fill-in-the-blank/
-
GitHub – labmlai/annotated_deep_learning_paper_implementations: 🧑🏫 Implementation s/tutorials of deep learning papers with side-by-side notes 📝; including transformers ( original, xl, switch, feedback, vit), optimizers (adam, radam, adabelief), gans(…
https://github.com/labmlai/annotated_deep_learning_paper_implementations
-
15 August, 2021 11:40
https://syncedreview.com/2021/07/16/deepmind-podracer-tpu-based-rl-frameworks-deliver-exceptional-performance-at-low-cost-63/
-
9 August, 2021 21:20
https://medium.com/analytics-vidhya/serverless-your-machine-learning-model-with-pycaret-and-aws-lambda-c33334ee6011
-
Explaining the decisions of XGBoost models using counterfactual examples | by Pierre Blanchart | Jul, 2021 | Towards Data Science
https://towardsdatascience.com/explaining-the-decisions-of-xgboost-models-using-counterfactual-examples-fd9c57c83062
-
Why Is Everyone at Kaggle Obsessed with Optuna For Hyperparameter Tuning?
https://towardsdatascience.com/why-is-everyone-at-kaggle-obsessed-with-optuna-for-hyperparameter-tuning-7608fdca337c Why Is Everyone at Kaggle Obsessed with Optuna For Hyperparameter Tuning? | by Bex T. | Aug, 2021 | Towards Data Science After importing optuna, we define an objective that returns the function we want to minimize.. In the body of the objective, we define the parameters to be optimized, in this case, simple…
-
Cognitive Biases in the Political Arena
-
Getting Started with atoti
https://medium.com/atoti/getting-started-with-the-activeviam-python-library-for-data-science-28990b90d71c Getting Started with Atoti Atoti is a Python library and a JupyterLab extension to create data-viz widgets, such as pivot tables and charts in the notebook used to … medium.com
-
Small text: Active learning for text classification in Python
https://github.com/webis-de/small-text GitHub – webis-de/small-text: Active learning for text classification in Python Requires Python 3.7 or newer. For using the GPU, CUDA 10.1 or newer is required. Quick Start. For a quick start, see the provided examples for binary classification, pytorch multi-class classification, or transformer-based multi-class classification. Docs github.com
-
Open-Ended Learning Leads to Generally Capable Agents | DeepMind
https://deepmind.com/research/publications/open-ended-learning-leads-to-generally-capable-agents
-
Facebook AI Open-Sources ‘Droidlet’, A Platform For Building Robots With Natural Language Processing And Computer Vision To Understand The World Around Them | MarkTechPost
https://www.marktechpost.com/2021/07/30/facebook-ai-open-sources-droidlet-a-platform-for-building-robots-with-natural-language-processing-and-computer-vision-to-understand-the-world-around-them/
-
Introducing Triton: Open-Source GPU Programming for Neural Networks
https://openai.com/blog/triton/
-
Building MLGUI, user interfaces for machine learning applications | VentureBeat
https://venturebeat.com/2021/07/19/building-mlgui-user-interfaces-for-machine-learning-applications/
-
tunib-ai/parallelformers: Parallelformers: An Efficient Model Parallelization Toolkit for Deployment
https://github.com/tunib-ai/parallelformers
-
Unconventional Sentiment Analysis: BERT vs. Catboost | by Taras Baranyuk | Towards Data Science
https://towardsdatascience.com/unconventional-sentiment-analysis-bert-vs-catboost-90645f2437a9
-
18 July, 2021 15:43
Modin is targeted toward parallelizing the entire pandas API, without exception. This implies all pandas function can be used on MODIN. And this happens just by changing one line in code: import modin.pandas as pd https://daureducation.medium.com/bye-bye-pandas-3808348c48f1
-
Introducing the Standard Ping Test
https://techcommunity.microsoft.com/t5/azure-monitor/introducing-the-standard-ping-test/ba-p/2393325?utm_content=buffer501c5&utm_medium=social&utm_source=linkedin.com&utm_campaign=buffer Introducing the new Standard ping test in App Insights Our URL ping test has long been a simple way for customers to check their endpoints but lacks the complexity to meet all single request test needs. techcommunity.microsoft.com
-
BlenderBot 2.0: An open source chatbot that builds long-term memory and searches the internet
https://parl.ai/projects/blenderbot2/
-
NLP needs to be open. 500+ researchers are trying to make it happen | VentureBeat
https://venturebeat-com.cdn.ampproject.org/c/s/venturebeat.com/2021/07/14/nlp-needs-to-be-open-500-researchers-are-trying-to-make-it-happen/amp/
-
artefactory/NLPretext: All the goto functions you need to handle NLP use-cases, integrated in NLPretext
https://github.com/artefactory/NLPretext
-
Deep learning on graph for nlp
https://drive.google.com/file/d/1A9Gtzyan4tqFTgmNsNfwOkO4ELR77iNh/view
-
Biases in AI Systems – ACM Queue
https://queue.acm.org/detail.cfm?id=3466134
-
Dataiku – Analyze text data with ontology tagging
https://www.dataiku.com/product/plugins/nlp-analysis/
-
ggside: Plot Linear Regression using Marginal Distributions (ggplot2 extension)
https://www.business-science.io/code-tools/2021/05/18/marginal_distributions.html ggside: Plot Linear Regression using Marginal Distributions (ggplot2 extension) Business Science Data Science Courses for Business. Learn the data science skills to accelerate your career in 6-months or less.. 5-10 Hours Per Week. 80/20 Tools. End-To-End Business Projects. www.business-science.io
-
BERT as a service
https://github.com/dimitreOliveira/bert-as-a-service_TFX GitHub – dimitreOliveira/bert-as-a-service_TFX: End-to-end pipeline with TFX to train and deploy a BERT model for sentiment analysis. BERT as a service This repository is designed to demonstrate a simple yet complete machine learning solution that uses a BERT model for text sentiment analysis using a TensorFlow Extended end-to-end pipeline, and making use of some…
-
Transfer Learning with 5 lines of code
https://medium.com/deepquestai/transfer-learning-with-5-lines-of-code-5e69d0290850 Transfer Learning with 5 lines of code | by Moses Olafenwa | DeepQuestAI | Medium In the field of modern Artificial Intelligence, Deep Learning has proved to be single most accurate methods to train intelligent models which can match and effectively augment human intelligence in… medium.com
-
Not Enough Data? GPT-3 to the rescue!
https://techcommunity.microsoft.com/t5/ai-customer-engineering-team/not-enough-data-gpt-3-to-the-rescue/ba-p/2495144 Not Enough Data? GPT-3 to the rescue! “I don’t have enough relevant data for my project”! Nearly every data scientist has uttered this sentence at least once. When developing robust machine learning models, we typically require a large amount of high-quality data. Obtaining such data and more so, labelled or annotated data can be…
-
ImageAI
https://medium.com/deepquestai/transfer-learning-with-5-lines-of-code-5e69d0290850 Transfer Learning with 5 lines of code | by Moses Olafenwa | DeepQuestAI | Medium In the field of modern Artificial Intelligence, Deep Learning has proved to be single most accurate methods to train intelligent models which can match and effectively augment human intelligence in… medium.com
-
BERT as a service
https://github.com/dimitreOliveira/bert-as-a-service_TFX GitHub – dimitreOliveira/bert-as-a-service_TFX: End-to-end pipeline with TFX to train and deploy a BERT model for sentiment analysis. BERT as a service This repository is designed to demonstrate a simple yet complete machine learning solution that uses a BERT model for text sentiment analysis using a TensorFlow Extended end-to-end pipeline, and making use of some…
-
Trankit: A Light-Weight Transformer-based Python Toolkit for Multilingual Natural Language Processing
https://github.com/nlp-uoregon/trankit GitHub – nlp-uoregon/trankit: Trankit is a Light-Weight Transformer-based Python Toolkit for Multilingual Natural Language Processing Trankit outperforms the current state-of-the-art multilingual toolkit Stanza (StanfordNLP) in many tasks over 90 Universal Dependencies v2.5 treebanks of 56 different languages while still being efficient in memory usage and speed, making it usable for general users. In particular,…
-
GitHub – mingrammer/diagrams: Diagram as Code for prototyping cloud system architectures
https://github.com/mingrammer/diagrams
-
Home | 20 Patterns in Software Teams
https://alpiepho.github.io/gitprime-patterns/
-
7 June, 2021 11:26
https://towardsdatascience.com/transformers-explained-visually-not-just-how-but-why-they-work-so-well-d840bd61a9d3
-
Few-shot learning in practice: GPT-Neo and the 🤗 Accelerated Inference API
https://huggingface.co/blog/few-shot-learning-gpt-neo-and-inference-api
-
Extract values and line items from invoices with Form Recognizer now generally available – Microsoft Tech Community
https://techcommunity.microsoft.com/t5/azure-ai/extract-values-and-line-items-from-invoices-with-form-recognizer/ba-p/2414729?utm_content=bufferc63ab&utm_medium=social&utm_source=linkedin.com&utm_campaign=buffer
-
The 10 Best Data Preparation Tools and Software for 2021
https://solutionsreview.com/data-integration/the-best-data-preparation-tools-and-software/
-
An introduction to Recommendation Systems: an overview of machine and deep learning architectures
https://theaisummer.com/recommendation-systems An introduction to Recommendation Systems: an overview of machine and deep learning architectures | AI Summer Learn about the SOTA recommender system models. From collaborative filtering and factorization machines to DCN and DLRM theaisummer.com
-
Awesome Open Source
https://awesomeopensource.com/ Find Open Source By Searching, Browsing and Combining 7,000 Topics Find Useful Open Source By Browsing and Combining 7,000 Topics In 59 Categories, Spanning The Top 371,460 Projects awesomeopensource.com