Catégorie : Machine Learning
-
AllenNLP Project Gallery
https://gallery.allennlp.org/
-
Word Mover’s Distance for Text Similarity
https://towardsdatascience.com/word-movers-distance-for-text-similarity-7492aeca71b0 Word Mover’s Distance for Text Similarity | by Nihit Saxena | Towards Data Science – Medium Introduction of the NLP (Natural Language Processing) revolutionized all the industries. So, NLP is a branch of AI (artificial Intelligence) that helps computer understand, interpret and manipulate human language. Now, with heaps of data available (thanks to big…
-
Google Brain Introduces Symbolic Programming + PyGlove Library to Reformulate AutoML | by Synced | Feb, 2021 | Medium
https://medium.com/@Synced/google-brain-introduces-symbolic-programming-pyglove-library-to-reformulate-automl-bde1d60cb8f6
-
The Best of NLP
https://cacm.acm.org/magazines/2021/4/251336-the-best-of-nlp/fulltext The Best of NLP | April 2021 | Communications of the ACM "Each time, the added scale gives us new capabilities to let us test new assumptions," Bosselut says. "As much as many people think we are going too far down this path, the truth is that the next iteration of language modeling could…
-
DeepMoji
https://medium.com/@bjarkefelbo/what-can-we-learn-from-emojis-6beb165a5ea0 https://github.com/bfelbo/DeepMoji bfelbo/DeepMoji State-of-the-art deep learning model for analyzing sentiment, emotion, sarcasm etc. – bfelbo/DeepMoji github.com
-
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
https://arxiv.org/abs/2005.11401 https://huggingface.co/transformers/master/model_doc/rag.html#tfragmodel "My biggest-challenge open-source collaboration with Huggingface : Tensorflow’s implementation of RAG (Retrieval Augmented Generation) is now available on Huggingface master !!! https://lnkd.in/gGVmw4X RAG ( https://lnkd.in/gdKWqqZ ) is an AI prototype that can read articles to give answers to any questions! With appropriate training data like ELI5 ( https://lnkd.in/gB4S4wj ) , it can even…
-
Way beyond AlphaZero: Berkeley and Google work shows robotics may be the deepest machine learning of all | ZDNet
https://www.zdnet.com/article/way-beyond-alphazero-berkeley-and-google-work-shows-robotics-may-be-the-deepest-machine-learning-of-all/?utm_content=buffere4883&utm_medium=social&utm_source=twitter.com&utm_campaign=buffer
-
NLP Text-Classification in Python: PyCaret Approach Vs The Traditional Approach
https://towardsdatascience.com/nlp-classification-in-python-pycaret-approach-vs-the-traditional-approach-602d38d29f06 NLP Text-Classification in Python: PyCaret Approach Vs The Traditional Approach | by Prateek Baghel | Towards Data Science I. Introduction. In this post we’ll see a demonstration of an NLP-Classification problem with 2 different approaches in python: 1-The Traditional approach: In this approach, we will: – preprocess the given text d ata using different…
-
SEO Turns to Data Graphs to Learn About the Web – Go Fish Digital
https://gofishdigital-com.cdn.ampproject.org/c/s/gofishdigital.com/data-graph/amp/
-
14 free or affordable online courses to learn Python, offered by MIT, Harvard, UPenn, Google, and more
https://www.businessinsider.com/how-to-learn-python?_lrsc=eda1cd61-8077-4229-8cb0-1e997906fb46#learning-python-3 14 free or affordable online courses to learn Python, offered by MIT, Harvard, UPenn, Google, and more Python is one of the most popular programming languages used in everything from data analysis to AI. Here are some of the best classes to learn it. www.businessinsider.com
-
Doccano – An open-source text annotation tool for humans.
An open-source text annotation tool for humans. Annotation features for : Text classification Sequence labeling Sequence to sequence tasks. Label data for: sentiment analysis, named entity recognition, text summarization and … Features: Collaborative annotation Multi-language support Mobile support Emoji 😄 support Dark theme RESTful API pip install doccano https://github.com/doccano/doccano GitHub – doccano/doccano: Open source text…
-
Open GPU Data Science | RAPIDS
https://rapids.ai/
-
Run VSCode (codeserver) on Google Colab or Kaggle Notebooks
https://github.com/abhishekkrthakur/colabcode
-
Language Models are Open Knowledge Graphs .. but are hard to mine!
https://towardsdatascience.com/language-models-are-open-knowledge-graphs-but-are-hard-to-mine-13e128f3d64d Language Models are Open Knowledge Graphs .. but are hard to mine! Join me as I dive into the latest research on creating knowledge graphs using transformer based language models towardsdatascience.com
-
GitHub – jalammar/ecco: Visualize and explore NLP language models. Ecco creates interactive visualizations directly in Jupyter notebooks explaining the behavior of Transformer-based language models (like GPT2).
https://github.com/jalammar/ecco
-
Data Science Infographic
https://github.com/dataprofessor/infographic GitHub – dataprofessor/infographic: Infographic Number Title Preview YouTube Video; 01: Building the Machine Learning Model. Construindo um Modelo Supervisionado de Machine Learning (Portugese Translation of "Building the Machine Learning Model") github.com
-
CLIP: Connecting Text and Images
https://openai.com/blog/clip/
-
MLOps Tooling Landscape v2
https://huyenchip.com/2020/12/30/mlops-v2.html MLOps Tooling Landscape v2 (+84 new tools) – Dec ’20 Last June, I published the post What I learned from looking at 200 machine learning tools.The post got some attention and I got a lot of messages from people telling me about new tools. I updated the old list to now include 284 tools.…
-
The Pile An 800GB Dataset of Diverse Text for Language Modeling
https://pile.eleuther.ai/ The Pile The Pile is a 825 GiB diverse, open source language modelling data set that consists of 22 smaller, high-quality datasets combined together. pile.eleuther.ai
-
Classifying Sentiment from Text Reviews
https://towardsdatascience.com/classifying-sentiment-from-text-reviews-a2c65ea468d6
-
Google, Apple, and others show large language models trained on public data expose personal information | VentureBeat
https://venturebeat.com/2020/12/16/google-apple-and-others-show-large-language-models-trained-on-public-data-expose-personal-information/
-
GitHub – WillianFuks/tfcausalimpact: Google’s Causal Impact Algorithm Implemented on Top of TensorFlow Probability
https://github.com/WillianFuks/tfcausalimpact
-
GitHub – graphdeeplearning/graphtransformer: Source code for « A Generalization of Transformer Networks to Graphs », DLG-AAAI’21.
We propose a generalization of transformer neural network architecture for arbitrary graphs: Graph Transformer. https://github.com/graphdeeplearning/graphtransformer
-
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~!
-
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~!
-
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,…
-
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
-
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
-
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
-
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
-
GitHub – alihussainia/openvino-colab: OpenVINO Edge AI Applications deployment on Google Colaboratory
https://github.com/alihussainia/openvino-colab
-
Hugging Face Transformers – Get started !
https://www.kaggle.com/funtowiczmo/hugging-face-transformers-get-started Hugging Face Transformers – Get started ! | Kaggle We use cookies on Kaggle to deliver our services, analyze web traffic, and improve your experience on the site. By using Kaggle, you agree to our use of cookies. www.kaggle.com
-
An introduction to transfer learning in NLP and HuggingFace with Thomas Wolf – YouTube
https://m.youtube.com/watch?v=t86G11tfVNw
-
google-research/vision_transformer
https://github.com/google-research/vision_transformer
-
What I learned from looking at 200 machine learning tools
https://huyenchip.com/2020/06/22/mlops.html
-
kelvins/awesome-mlops: A curated list of awesome MLOps tools
https://github.com/kelvins/awesome-mlops
-
ML Inference on Edge devices with ONNX Runtime using Azure DevOps+MLOps – Microsoft Tech Community
https://techcommunity.microsoft.com/t5/ai-customer-engineering-team/ml-inference-on-edge-devices-with-onnx-runtime-using-azure/ba-p/1737331?WT.mc_id=DOP-MVP-4025064&utm_content=bufferfd11e&utm_medium=social&utm_source=linkedin.com&utm_campaign=buffer
-
4 Python AutoML Libraries Every Data Scientist Should Know
https://towardsdatascience.com/4-python-automl-libraries-every-data-scientist-should-know-680ff5d6ad08
-
GitHub – deepset-ai/haystack: Transformers at scale for question answering & neural search. Using NLP via a modular Retriever-Reader-Pipeline. Supporting DPR, Elasticsearch, HuggingFace’s Modelhub…
https://github.com/deepset-ai/haystack/
-
Deep Learning on Graphs
http://cse.msu.edu/~mayao4/dlg_book/
-
18 September, 2020 07:25
https://towardsdatascience.com/pycaret-2-1-is-here-whats-new-4aae6a7f636a
-
Google TAPAS is a BERT-Based Model to Query Tabular Data Using Natural Language | by Jesus Rodriguez | DataSeries | Sep, 2020 | Medium
https://medium.com/dataseries/google-tapas-is-a-bert-based-model-to-query-tabular-data-using-natural-language-2435a386b43f
-
GitHub – huggingface/datasets: 🤗 Fast, efficient, open-access datasets and evaluation m etrics for Natural Language Processing in PyTorch, TensorFlow, NumPy and Pandas
https://github.com/huggingface/datasets
-
GitHub – huggingface/pytorch_block_sparse: Fast Block Sparse Matrices for Pytorch
https://github.com/huggingface/pytorch_block_sparse
-
Plotly Python Open Source Graphing Library
https://plotly.com/python/#ai_ml Plotly Python Graphing Library | Python | Plotly Interactive Data Analysis with FigureWidget ipywidgets. View Tutorial. Click Events plotly.com
-
Announcing Neo4j Aura on Google Cloud Platform
https://neo4j.com/blog/announcing-neo4j-aura-on-google-cloud-platform/ Announcing Neo4j Aura on Google Cloud Platform Today, Neo4j is proud to announce the general availability of Neo4j Aura™ on Google Cloud Platform (GCP).Neo4j Aura is the first and only integrated graph database service on GCP. If you haven’t seen it yet, Aura is the simplest way to run Neo4j in the cloud. Completely…