Catégorie : Notes
-
Document Streaming With FastAPI, Apache Kafka, Apache Spark, MongoDB
https://learndataengineering.com/p/document-streaming
-
Researchers Propose a Novel Framework ‘LilNetX’ For Training Deep Neural Network With Extreme Model Compression, and Structured Sparsification – MarkTechPost
https://www-marktechpost-com.cdn.ampproject.org/c/s/www.marktechpost.com/2022/04/12/researchers-propose-a-novel-framework-lilnetx-for-training-deep-neural-network-with-extreme-model-compression-and-structured-sparsification/?amp
-
Creating Confidence Intervals for Machine Learning Classifiers
https://sebastianraschka.com/blog/2022/confidence-intervals-for-ml.html
-
The EASIEST! way to do Text Classification with spaCy and Classy Classification – YouTube
https://m.youtube.com/watch?v=qLux8NfSEQQ
-
GitHub – mingrammer/diagrams: Diagram as Code for prototyping cloud system architectures
https://github.com/mingrammer/diagrams
-
Converse Task-Oriented Dialogue System Simplifies Chatbot Building, Handles Complex Tasks
https://blog.salesforceairesearch.com/converse-task-oriented-dialogue-system/ Converse Task-Oriented Dialogue System Simplifies Chatbot Building, Handles Complex Tasks What Makes Converse Unique and Powerful. Simplifies Bot Building While Handling Complex Tasks Other chatbot building tools require bot builders to script every step of the conversation, requiring a great deal of effort to handle the meandering, dynamic nature of human conversation — for…
-
25 April, 2022 08:25
https://www.quansight.com/post/dash-voila-panel-streamlit-our-thoughts-on-the-big-four-dashboarding-tools Dash, Voila, Panel, & Streamlit—Our Thoughts on the Big Four Dashboarding Tools On the other end, we have business intelligence or BI Tools. These are commercial platforms like Tableau and PowerBI. These tools are great if you have tabular data or are pulling from a database and content with the prepackaged visualization options. www.quansight.com
-
MLOps with Databricks: (I) process flow design
https://medium.com/@pdemeulenaer/mlops-with-databricks-i-process-flow-design-2293bbe03e45 MLOps with Databricks: (I) process flow design | by Philippe de Meulenaer | Apr, 2022 | Medium Adaptation of the MLOps maturity “level 2” from Google. Without repeating the Google blog post, the most important aspects of this process flow are: medium.com
-
Google AI Blog: Pix2Seq: A New Language Interface for Object Detection
https://ai.googleblog.com/2022/04/pix2seq-new-language-interface-for.html?m=1
-
Best Practices for Visualizing Your Cluster Results
Proven techniques for cluster visualization and interpretation https://towardsdatascience.com/best-practices-for-visualizing-your-cluster-results-20a3baac7426
-
GitHub – tomkerkhove/azure-apim-on-container-apps: Playground to run Azure API Management’s self-hosted gateway on Azure Container Apps
https://github.com/tomkerkhove/azure-apim-on-container-apps
-
Meta AI Researchers Built An End-To-End Machine Learning Platform Called Looper, With Easy-To-Use APIs For Decision-Making And Feedback Collection – MarkTechPost
https://www.marktechpost.com/2022/04/22/meta-ai-researchers-built-an-end-to-end-machine-learning-platform-called-looper-with-easy-to-use-apis-for-decision-making-and-feedback-collection/
-
Embracing an ML-first mindset helps startups accelerate time-to-market and build long-term competitiveness | VentureBeat
https://venturebeat-com.cdn.ampproject.org/c/s/venturebeat.com/2022/04/21/embracing-an-ml-first-mindset-helps-startups-accelerate-time-to-market-and-build-long-term-competitiveness/amp/
-
Crosslingual Coreference
https://github.com/Pandora-Intelligence/crosslingual-coreference GitHub – Pandora-Intelligence/crosslingual-coreference: A multi-lingual approach to AllenNLP CoReference Resolution along with a wrapper for spaCy. A multi-lingual approach to AllenNLP CoReference Resolution along with a wrapper for spaCy. – GitHub – Pandora-Intelligence/crosslingual-coreference: A multi-lingual approach to AllenNLP CoReferenc… github.com
-
The Intuitions Behind Knowledge Graphs and Reasoning
https://www.oxfordsemantic.tech/blog/the-intuitions-behind-knowledge-graphs-and-reasoning The Intuitions Behind Knowledge Graphs and Reasoning | Sep 17, 2021 | Oxford Semantic Technologies The IF part of the rule is also called the body or antecedent.; The THEN part of the rule is called the head or the consequent.; The head is written first, and is separated from the body by the…
-
Algorithms for Decision Making
https://algorithmsbook.com/
-
GitHub – Azure/Mission-Critical: This repository provides a design methodology and approach to building highly-reliable applications on Microsoft Azure for mission-critical workloads.
https://github.com/Azure/Mission-Critical
-
Latest Paper From Amazon AI Research Analyzes And Explains The Challenges And Developments in The Field Of Federated Learning
https://www.marktechpost.com/2022/04/17/latest-paper-from-amazon-ai-research-analyzes-and-explains-the-challenges-and-developments-in-the-field-of-federated-learning/ Latest Paper From Amazon AI Research Analyzes And Explains The Challenges And Developments in The Field Of Federated Learning – MarkTechPost This article summary is based on the research paper from Amazon: ‘Federated learning challenges and opportunities: An outlook’ All credits for this research goes to the authors of this paper. 👏 👏 👏…
-
Meet DeepDPM: No Predefined Number of Clusters Needed for Deep Clustering Tasks
https://syncedreview.com/2022/04/18/meet-deepdpm-no-predefined-number-of-clusters-needed-for-deep-clustering-tasks/ Meet DeepDPM: No Predefined Number of Clusters Needed for Deep Clustering Tasks | Synced Deep neural networks (DNNs) have achieved great success across a wide variety of tasks, including fundamental unsupervised tasks such as data clustering. Like conventional clustering methods, deep clustering is also parametric, meaning it requires a predefined cluster or class number.…
-
Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language
https://socraticmodels.github.io/
-
Microsoft Research Introduces Open Data for Social Impact Framework – MarkTechPost
https://www.marktechpost.com/2022/04/16/microsoft-research-introduces-open-data-for-social-impact-framework/
-
LinkedIn Open-Sources ‘Feathr’, It’s Feature Store To Simplify Machine Learning (ML) Feature Management And Improve Developer Productivity – MarkTechPost
https://www.marktechpost.com/2022/04/15/linkedin-open-sources-feathr-its-feature-store-to-simplify-machine-learning-ml-feature-management-and-improve-developer-productivity/
-
These Are the 10 Best Lesser-Known Python Libraries You Should Know About
https://towardsdatascience.com/these-are-the-10-best-lesser-known-python-libraries-you-should-know-about-9c551842fc39 These Are the 10 Best Lesser-Known Python Libraries You Should Know About | by Ismael Araujo | Apr, 2022 | Towards Data Science Data Science is changing faster than ever, and in learning how to improve our productivity, we need to create some shortcuts, and Python libraries are great for that. If you are…
-
Recommendation System Tutorial with Python using Collaborative Filtering
https://pub.towardsai.net/recommendation-system-in-depth-tutorial-with-python-for-netflix-using-collaborative-filtering-533ff8a0e444
-
Google Builds Language Models with Socratic Dialogue to Improve Zero-Shot Multimodal Reasoning Capabilities | Synced
https://syncedreview.com/2022/04/12/google-builds-language-models-with-socratic-dialogue-to-improve-zero-shot-multimodal-reasoning-capabilities/
-
GitHub – ikergarcia1996/MetaVec: A monolingual and cross-lingual meta-embedding generation and evaluation framework
https://github.com/ikergarcia1996/MetaVec
-
A brief timeline of NLP from Bag of Words to the Transformer family | by Fabio Chiusano | NLPlanet | Feb, 2022 | Medium
https://medium.com/nlplanet/a-brief-timeline-of-nlp-from-bag-of-words-to-the-transformer-family-7caad8bbba56
-
1907.10903 DropEdge: Towards Deep Graph Convolutional Networks on Node Classification
https://arxiv.org/abs/1907.10903
-
Towards General-Purpose Minecraft AI Agents
https://blog.singularitynet.io/towards-general-purpose-minecraft-ai-agents-41fe415d6dd
-
Feature Propagation is a simple and surprisingly efficient solution for learning on graphs with missing node features | by Michael Bronstein | Feb, 2022 | Towards Data Science
https://towardsdatascience.com/learning-on-graphs-with-missing-features-dd34be61b06
-
Bayesian Hyperparameter Optimization with tune-sklearn in PyCaret
https://medium.com/distributed-computing-with-ray/bayesian-hyperparameter-optimization-with-tune-sklearn-in-pycaret-a33b1592662f Bayesian Hyperparameter Optimization with tune-sklearn in PyCaret | by Antoni Baum | Distributed Computing with Ray – Medium Here’s a situation every PyCaret user is familiar with: after selecting a promising model or two from compare_models(), it’s time to tune its hyperparameters to squeeze out all of the model’s… medium.com
-
Google & J.P. Morgan Propose Advanced Bandit Sampling for Multiplex Networks
https://syncedreview.com/2022/02/10/deepmind-podracer-tpu-based-rl-frameworks-deliver-exceptional-performance-at-low-cost-203/ Google & J.P. Morgan Propose Advanced Bandit Sampling for Multiplex Networks | Synced Graph neural networks (GNNs) have gained popularity in the AI research community due to their impressive performance in high-impact applications such as drug discovery and social network analyses. Most existing studies on GNNs however have focused on "monoplex" settings (networks with…
-
imodels: A Python Package For Fitting Interpretable Machine Learning Models
https://github.com/csinva/imodels csinva/imodels: Interpretable ML package 🔍 for concise, transparent, and accurate predictive modeling (sklearn-compatible). – GitHub Interpretable ML package 🔍 for concise, transparent, and accurate predictive modeling (sklearn-compatible). – GitHub – csinva/imodels: Interpretable ML package 🔍 for concise, transparent, and accurate predictive modeling (sklearn-compatible). github.com
-
Improve high-value research with Hugging Face and Amazon SageMaker asynchronous inference endpoints | AWS Machine Learning Blog
https://aws.amazon.com/fr/blogs/machine-learning/improve-high-value-research-with-hugging-face-and-amazon-sagemaker-asynchronous-inference-endpoints/
-
Explainable Boosting Machines
Keeping accuracy high while getting suggestive explanations that create knowledge and help understand and debug data. https://pub.towardsai.net/explainable-boosting-machines-c71b207231b5
-
yzpang/gold-off-policy-text-gen-iclr21
https://github.com/yzpang/gold-off-policy-text-gen-iclr21
-
D-Tale bring you an easy way to view & analyze Pandas data structures
https://github.com/man-group/dtale GitHub – man-group/dtale: Visualizer for pandas data structures Visualizer for pandas data structures. Contribute to man-group/dtale development by creating an account on GitHub. github.com
-
Data Distribution Shifts and Monitoring
https://huyenchip.com/2022/02/07/data-distribution-shifts-and-monitoring.html
-
Drive 2x Performance into Your Scikit-learn Machine Learning Tasks
https://www.intel.com/content/www/us/en/developer/videos/drive-innovation-performance-scikit-learn-ml-tasks.html?cid=psm&source=facebook_soc_ih&campid=ww_1ai_satg&content=vid-idz_ai-seg&fbclid=IwAR1_PuI8FBDBf4XTxLh6yhTHhFJPU6mrlv4idaHo1WnWdhGWKW-bz2F_jqs#gs.ogdi00
-
Shapash – A Python library which aims to make machine learning interpretable and understandable to everyone.
https://shapash.readthedocs.io/en/latest/# Welcome to Shapash’s documentation ! — Shapash 1.6.1 documentation Welcome to Shapash’s documentation !¶ Shapash is a Python library which aims to make machine learning interpretable and understandable to everyone.Shapash provides several types of visualization which displays explicit labels that everyone can understand. Data Scientists can more easily understand their models and share their…
-
Scalable Efficient Big Data Pipeline Architecture | Towards Data Science
https://towardsdatascience.com/scalable-efficient-big-data-analytics-machine-learning-pipeline-architecture-on-cloud-4d59efc092b5
-
DARWIN: Data Science and Artificial Intelligence Workbench at LinkedIn
https://engineering.linkedin.com/blog/2022/darwin–data-science-and-artificial-intelligence-workbench-at-li DARWIN: Data Science and Artificial Intelligence Workbench at LinkedIn | LinkedIn Engineering Co-authors: Varun Saxena, Harikumar Velayutham, and Balamurugan Gangadharan LinkedIn is the largest global professional network and generates massive amounts of high-quality data. Our data infrastructure scales to store exabytes of data; data analysts, data scientists, and AI engineers then use this data…
-
Lean ML
https://towardsdatascience.com/lean-ml-c003511b29a1 Lean ML. How do the principles of Lean Software… | by John Mackie | Towards Data Science Kanban board on Microsoft Azure (image by author) Before I do anything on a project I m ake sure I have my Kanban board setup! In the spirit of staying lean it doesn’t get much simpler to…
-
axa-group/Parsr: Transforms PDF, Documents and Images into Enriched Structured Data
https://github.com/axa-group/Parsr
-
n8n Extendable workflow automation
https://docs.n8n.io/
-
cerlymarco/shap-hypetune: A python package for simultaneous Hyperparameters Tuning and Features Selection for Gradient Boosting Models.
https://github.com/cerlymarco/shap-hypetune
-
The Simple Math behind 3 Decision Tree Splitting criterions | by Rahul Agarwal | Towards Data Science
https://towardsdatascience.com/the-simple-math-behind-3-decision-tree-splitting-criterions-85d4de2a75fe
-
30 January, 2022 07:28
https://github.com/kubeflow-kale/kale