Conversational AI
In this video, Merve Noyan, Google Developer Expert on Machine Learning, gives an overview of the conversational AI niche. The talk is hosted by Alexey Grigorev, the founder of DataTalks.Club.
https://bit.ly/35ESW4d
In this video, Merve Noyan, Google Developer Expert on Machine Learning, gives an overview of the conversational AI niche. The talk is hosted by Alexey Grigorev, the founder of DataTalks.Club.
https://bit.ly/35ESW4d
YouTube
Conversational AI - Merve Noyan
Start from 15:45 (YouTube doesn't let me cut this video)
Links:
- Merve's Twitter: https://twitter.com/mervenoyann
- Merve's podcast: https://www.youtube.com/channel/UCU-KsNFmnZ_v3RZ7MKvCzDg
- cs224n course: http://web.stanford.edu/class/cs224n/
- Rasa…
Links:
- Merve's Twitter: https://twitter.com/mervenoyann
- Merve's podcast: https://www.youtube.com/channel/UCU-KsNFmnZ_v3RZ7MKvCzDg
- cs224n course: http://web.stanford.edu/class/cs224n/
- Rasa…
Deep Learning Do It Yourself!
The website is a collection of more than 20 modules on learning deep learning. As a student, you can walk through the modules at your own pace and interact with others. You can also contribute to the materials by adding new modules yourself.
https://bit.ly/3vMub0l
#DataScienceDigest #DataScience #MachineLearning #ArtificialIntelligence #AI #ML #deeplearning
Subscribe to our weekly newsletter — https://bit.ly/3cS4G7y
The website is a collection of more than 20 modules on learning deep learning. As a student, you can walk through the modules at your own pace and interact with others. You can also contribute to the materials by adding new modules yourself.
https://bit.ly/3vMub0l
#DataScienceDigest #DataScience #MachineLearning #ArtificialIntelligence #AI #ML #deeplearning
Subscribe to our weekly newsletter — https://bit.ly/3cS4G7y
Comparing Test Sets with Item Response Theory
In this paper, Clara Vania et al. use the Item Response Theory to evaluate 29 datasets using predictions from 18 pretrained Transformer models on individual test examples. Quoref, HellaSwag, and MC-TACO are best suited for distinguishing among state-of-the-art models, while SNLI, MNLI, and CommitmentBank seem to be saturated for current strong models.
https://bit.ly/3xHDkJj
In this paper, Clara Vania et al. use the Item Response Theory to evaluate 29 datasets using predictions from 18 pretrained Transformer models on individual test examples. Quoref, HellaSwag, and MC-TACO are best suited for distinguishing among state-of-the-art models, while SNLI, MNLI, and CommitmentBank seem to be saturated for current strong models.
https://bit.ly/3xHDkJj
How Airbnb Standardized Metric Computation at Scale
The engineering team of Airbnb reveals the design principles of Minerva compute infrastructure. Minerva is a single source of truth metric platform that standardizes the way business metrics are created, computed, served, and consumed. The article features the link to the first post on Minerva. Check it out, too!
https://bit.ly/3zLDv8g
The engineering team of Airbnb reveals the design principles of Minerva compute infrastructure. Minerva is a single source of truth metric platform that standardizes the way business metrics are created, computed, served, and consumed. The article features the link to the first post on Minerva. Check it out, too!
https://bit.ly/3zLDv8g
Medium
How Airbnb Standardized Metric Computation at Scale
Part II: The six design principles of Minerva compute infrastructure
AI Can Now Emulate Text Style in Images in One Shot — Using Just a Single Word
In this article, the engineering team of Facebook AI presents TextStyleBrush, an AI research project that can copy the style of text in a photo using just a single word. With this AI model, you can edit and replace text in images. The team hopes to spur dialogue and research into detecting potential misuse of this type of technology, so make sure to contribute.
https://bit.ly/3wU3t7I
In this article, the engineering team of Facebook AI presents TextStyleBrush, an AI research project that can copy the style of text in a photo using just a single word. With this AI model, you can edit and replace text in images. The team hopes to spur dialogue and research into detecting potential misuse of this type of technology, so make sure to contribute.
https://bit.ly/3wU3t7I
Facebook
AI can now emulate text style in images in one shot — using just a single word
Today, we’re introducing TextStyleBrush, the first self-supervised AI model that replaces text in existing images of both scenes and handwriting — in one shot — using just a single example word.
Data Science Digest — 24.06.21
The new issue of DataScienceDigest is here! The impact of NLP and the growing budgets to drive AI transformations. How Airbnb standardized metric computation at scale. Cross-Validation, MASA-SR, AgileGAN, EfficientNetV2, and more…
https://bit.ly/3qnuy0u
Join 👉@DataScienceDigest
The new issue of DataScienceDigest is here! The impact of NLP and the growing budgets to drive AI transformations. How Airbnb standardized metric computation at scale. Cross-Validation, MASA-SR, AgileGAN, EfficientNetV2, and more…
https://bit.ly/3qnuy0u
Join 👉@DataScienceDigest
Ingestion and Historization in the Data Lake
In this video, Alexey Grigorev, the founder of DataTalks.Club, hosts Illia Todor, Data Engineer, to talk about ingestion and historization of data in the data lake.
https://bit.ly/3zWKaMP
In this video, Alexey Grigorev, the founder of DataTalks.Club, hosts Illia Todor, Data Engineer, to talk about ingestion and historization of data in the data lake.
https://bit.ly/3zWKaMP
YouTube
Ingestion and Historization in the Data Lake - Illia Todor
Links
- Slides: https://www.slideshare.net/IlyaTodor/ingestion-and-historization-in-the-data-lake
- Feedback form: https://forms.gle/YByeD5GKsLuiVQEF8
Join DataTalks.Club: https://datatalks.club/slack.html
Our events: https://datatalks.club/events.html…
- Slides: https://www.slideshare.net/IlyaTodor/ingestion-and-historization-in-the-data-lake
- Feedback form: https://forms.gle/YByeD5GKsLuiVQEF8
Join DataTalks.Club: https://datatalks.club/slack.html
Our events: https://datatalks.club/events.html…
MLOps Toys
The platform is a collection of MLOps projects by category, including data versioning, training orchestration, feature store, experiment tracking, model serving, model monitoring, and explainability.
https://bit.ly/3xV97GF
The platform is a collection of MLOps projects by category, including data versioning, training orchestration, feature store, experiment tracking, model serving, model monitoring, and explainability.
https://bit.ly/3xV97GF
mlops.toys
MLOps Toys | A Curated List of Machine Learning Projects
Check out this curated list of the most useful MLOps tools, projects and more. Have something to add? Let us know!
DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification
In this research, Yongming Rao et al. propose a dynamic token sparsification framework to prune redundant tokens progressively and dynamically based on the input. A lightweight prediction module can estimate the importance score of each token given the current features. The module is added to different layers to prune redundant tokens hierarchically.
Web Page — https://bit.ly/3dgESlq
Paper — https://bit.ly/3xWf5XJ
Code — https://bit.ly/3jlUtUK
In this research, Yongming Rao et al. propose a dynamic token sparsification framework to prune redundant tokens progressively and dynamically based on the input. A lightweight prediction module can estimate the importance score of each token given the current features. The module is added to different layers to prune redundant tokens hierarchically.
Web Page — https://bit.ly/3dgESlq
Paper — https://bit.ly/3xWf5XJ
Code — https://bit.ly/3jlUtUK
dynamicvit.ivg-research.xyz
DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification
Yongming Rao1 Wenliang Zhao1 Benlin Liu2
Jiwen Lu1 Jie Zhou1 Cho-Jui Hsieh2
1Tsinghua University 2University of California, Los Angeles
[Paper (arXiv)] …
Yongming Rao1 Wenliang Zhao1 Benlin Liu2
Jiwen Lu1 Jie Zhou1 Cho-Jui Hsieh2
1Tsinghua University 2University of California, Los Angeles
[Paper (arXiv)] …
Consistent Instance False Positive Improves Fairness in Face Recognition
In this paper, Xingkun Xu et al. propose a false positive rate penalty loss, a novel method to mitigate face recognition bias by increasing the consistency of instance False Positive Rate (FPR). The method requires no demographic annotations, allowing to mitigate bias among demographic groups divided by various attributes.
Paper — https://bit.ly/361fHiQ
Code — https://bit.ly/2UKAqoF
In this paper, Xingkun Xu et al. propose a false positive rate penalty loss, a novel method to mitigate face recognition bias by increasing the consistency of instance False Positive Rate (FPR). The method requires no demographic annotations, allowing to mitigate bias among demographic groups divided by various attributes.
Paper — https://bit.ly/361fHiQ
Code — https://bit.ly/2UKAqoF
The FLORES-101 Data Set: Helping Build Better Translation Systems Around the World
Building on the success of machine translation systems like M2M-100, Facebook AI has open-sourced FLORES-101, a many-to-many evaluation data set covering 101 languages from all over the world, to enable researchers to rapidly test and improve upon multilingual translation models like M2M-100. In this article, you’ll delve into its basics.
https://bit.ly/3hja98z
Building on the success of machine translation systems like M2M-100, Facebook AI has open-sourced FLORES-101, a many-to-many evaluation data set covering 101 languages from all over the world, to enable researchers to rapidly test and improve upon multilingual translation models like M2M-100. In this article, you’ll delve into its basics.
https://bit.ly/3hja98z
Facebook
The FLORES-101 data set: Helping build better translation systems around the world
Today we are open-sourcing FLORES-101, a first-of-its-kind, many-to-many evaluation data set covering 101 languages (10,100 translation directions) from all over the world.
Multivariate Probabilistic Regression with Natural Gradient Boosting
Natural Gradient Boosting (NGBoost) is a new method proposed by the researchers. It is based on nonparametrically modeling the conditional parameters of the multivariate predictive distribution. The method is robust, works out-of-the-box without extensive tuning, is modular with respect to the assumed target distribution, and performs competitively in comparison to existing approaches.
Paper — https://bit.ly/3haEF5C
Code — https://bit.ly/3qC1SB3
Natural Gradient Boosting (NGBoost) is a new method proposed by the researchers. It is based on nonparametrically modeling the conditional parameters of the multivariate predictive distribution. The method is robust, works out-of-the-box without extensive tuning, is modular with respect to the assumed target distribution, and performs competitively in comparison to existing approaches.
Paper — https://bit.ly/3haEF5C
Code — https://bit.ly/3qC1SB3
Data Phoenix Rises
We at Data Science Digest have always strived to ignite the fire of knowledge in the AI community. We’re proud to have helped thousands of people to learn something new and give you the tools to push ahead. And we’ve not been standing still, either.
Please meet Data Phoenix, a Data Science Digest rebranded and risen anew from our own flame. Our mission is to help everyone interested in Data Science and AI/ML to expand the frontiers of knowledge. More news, more updates, and webinars (!) are coming. Stay tuned!
Data Phoenix Digest — 01.07.2021
The new issue of Data Phoenix Digest is here! AI that helps write code, EU’s ban on biometric surveillance, genetic algorithms for NLP, multivariate probabilistic regression with NGBoosting, alias-free GAN, MLOps toys, and more…
https://bit.ly/3h722gE
Join 👉@DataPhoenix
We at Data Science Digest have always strived to ignite the fire of knowledge in the AI community. We’re proud to have helped thousands of people to learn something new and give you the tools to push ahead. And we’ve not been standing still, either.
Please meet Data Phoenix, a Data Science Digest rebranded and risen anew from our own flame. Our mission is to help everyone interested in Data Science and AI/ML to expand the frontiers of knowledge. More news, more updates, and webinars (!) are coming. Stay tuned!
Data Phoenix Digest — 01.07.2021
The new issue of Data Phoenix Digest is here! AI that helps write code, EU’s ban on biometric surveillance, genetic algorithms for NLP, multivariate probabilistic regression with NGBoosting, alias-free GAN, MLOps toys, and more…
https://bit.ly/3h722gE
Join 👉@DataPhoenix
What Is MLOps? — Everything You Must Know to Get Started
MLOps is a buzzword right now. Everyone talks about it; everybody wants to implement it and drive MLOps transformations. If you’re interested in what MLOps is too, this article will provide a scoop of ML systems development lifecycle and explain why you need MLOps.
https://bit.ly/3dB9gau
MLOps is a buzzword right now. Everyone talks about it; everybody wants to implement it and drive MLOps transformations. If you’re interested in what MLOps is too, this article will provide a scoop of ML systems development lifecycle and explain why you need MLOps.
https://bit.ly/3dB9gau
Medium
What is MLOps — Everything You Must Know to Get Started
A complete walkthrough of ML systems development lifecycle and need for MLOps
To Retrain, or Not to Retrain? Let’s Get Analytical About ML Model Updates
In this ML 101 article, you’ll find answers to questions like, «How often should I retrain a model?», «Should I retrain the model now?», and «Should I retrain, or should I update the model?». Dig in for an easy but important piece to read!
https://bit.ly/3qVwDRL
In this ML 101 article, you’ll find answers to questions like, «How often should I retrain a model?», «Should I retrain the model now?», and «Should I retrain, or should I update the model?». Dig in for an easy but important piece to read!
https://bit.ly/3qVwDRL
Evidentlyai
To retrain, or not to retrain? Let’s get analytical about ML model updates.
Is it time to retrain your machine learning model? Even though data science is all about… data, the answer to this question is surprisingly often based on a gut feeling. Can we do better?