U-GAT-IT
Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation
http://bit.ly/2N0Zlyr
Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation
http://bit.ly/2N0Zlyr
GitHub
taki0112/UGATIT
Official Tensorflow implementation of U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation (ICLR 2020) - taki0112/UGATIT
Data Science UA — 7th Conference on Machine Learning, Artificial Intelligence and Data Science in Kyiv. Productive networking and engineering insights. Over 500 participants and 20 speakers, 3 streams.
Buy tickets: http://bit.ly/2YKlfNp
10% promo code: DSUA_Digest
Buy tickets: http://bit.ly/2YKlfNp
10% promo code: DSUA_Digest
Advances in Conversational AI
New open-source data sets, algorithms, and models that improve five common weaknesses of open-domain chatbots today: consistency, specificity, empathy, knowledgeability, and multimodal understanding.
http://bit.ly/2MYTfyx
New open-source data sets, algorithms, and models that improve five common weaknesses of open-domain chatbots today: consistency, specificity, empathy, knowledgeability, and multimodal understanding.
http://bit.ly/2MYTfyx
Facebook
Advances in Conversational AI
Facebook AI has made scientific progress in improving nuanced conversational skills, including consistency, specificity, and empathy.
Ten simple rules for writing and sharing computational analyses in Jupyter Notebooks
These "simple rules" for Jupyter Notebooks amount to a set of best practices for ensuring that your work is maintainable, reproducible and easy to follow.
http://bit.ly/2YOasSG
These "simple rules" for Jupyter Notebooks amount to a set of best practices for ensuring that your work is maintainable, reproducible and easy to follow.
http://bit.ly/2YOasSG
journals.plos.org
Ten simple rules for writing and sharing computational analyses in Jupyter Notebooks
Last Chance to save 40% on tickets to the Deep Learning Summit, Europe
The world's leading Deep Learning Summit will be in London in September! Secure your summit pass with 40% off using code DSDIGEST.
https://bit.ly/2JN5Kv6
The world's leading Deep Learning Summit will be in London in September! Secure your summit pass with 40% off using code DSDIGEST.
https://bit.ly/2JN5Kv6
More pandas tricks!
Kevin Markham, founder of Data School has expanded his popular pandas tricks series. There are now more than 45 tricks and new ones are added daily.
http://bit.ly/2MZJal4
Kevin Markham, founder of Data School has expanded his popular pandas tricks series. There are now more than 45 tricks and new ones are added daily.
http://bit.ly/2MZJal4
Top 10 Best Podcasts on AI, Analytics, Data Science, Machine Learning
Check out KDnuggets list of Top 10 Most Popular Data Science and Machine Learning podcasts available on iTunes. Stay up to date in the field with these recent episodes and join in with the current data conversations.
http://bit.ly/2NekbdE
Check out KDnuggets list of Top 10 Most Popular Data Science and Machine Learning podcasts available on iTunes. Stay up to date in the field with these recent episodes and join in with the current data conversations.
http://bit.ly/2NekbdE
How to Implement Progressive Growing GAN Models in Keras
In this tutorial, you will discover how to develop progressive growing generative adversarial network models from scratch with Keras.
http://bit.ly/2NaEyIK
In this tutorial, you will discover how to develop progressive growing generative adversarial network models from scratch with Keras.
http://bit.ly/2NaEyIK
Machine Learning Mastery
How to Implement Progressive Growing GAN Models in Keras - Machine Learning Mastery
The progressive growing generative adversarial network is an approach for training a deep convolutional neural network model for generating synthetic images.
It is an extension of the more traditional GAN architecture that involves incrementally growing…
It is an extension of the more traditional GAN architecture that involves incrementally growing…
Parameter optimization in neural networks
Play with three interactive visualizations and develop your intuition for optimizing model parameters.
http://bit.ly/2Z2IQt1
Play with three interactive visualizations and develop your intuition for optimizing model parameters.
http://bit.ly/2Z2IQt1
www.deeplearning.ai
Parameter optimization in neural networks
Data Science Pioneers - Conquering the Next Frontier
Data Science Pioneers is a documentary investigating the future of data science with key data science leaders from across Europe and North America.
Trailer http://bit.ly/2Nl7DRO
http://bit.ly/2NjLCmE
Data Science Pioneers is a documentary investigating the future of data science with key data science leaders from across Europe and North America.
Trailer http://bit.ly/2Nl7DRO
http://bit.ly/2NjLCmE
Vimeo
Data Science Pioneers Excerpt - Triveni Ghandi @Dataiku
This is "Data Science Pioneers Excerpt - Triveni Ghandi @Dataiku" by Dataiku on Vimeo, the home for high quality videos and the people who love them.
Introducing the New Snorkel
Snorkel is a Python library for programmatically building and managing training datasets. In their latest update, the Snorkel Team walks through key new features, new tutorials, and the road ahead.
http://bit.ly/2NhrLV8
Snorkel is a Python library for programmatically building and managing training datasets. In their latest update, the Snorkel Team walks through key new features, new tutorials, and the road ahead.
http://bit.ly/2NhrLV8
74 Summaries of Machine Learning and NLP Research
These short summaries of Machine Learning and NLP research papers cover a wide variety of authors, topics and venues from the past couple of years. Includes key points, diagrams and links for each paper.
http://bit.ly/2D6nTjA
These short summaries of Machine Learning and NLP research papers cover a wide variety of authors, topics and venues from the past couple of years. Includes key points, diagrams and links for each paper.
http://bit.ly/2D6nTjA
Marek Rei
74 Summaries of Machine Learning and NLP Research - Marek Rei
My previous post on summarising 57 research papers turned out to be quite useful for people working in this field, so it is about time…
Hey folks,
Excited to announce that my team at VITech (VITech Lab) has released our first free Deep Learning Container at AWS Marketplace - http://bit.ly/DeepLearningContainer
This is a fully pre-configured docker container with TensorFlow 2.0 and open-source libraries for Machine Learning, including Jupyter Lab & Notebook, Keras, Theano, PyTorch, OpenCV, H2O, CNTK, NVIDIA CUDA, cuDNN, Numpy, Scipy, scikit-learn, XGBoost, etc. Use the container to reduce the time and resources spent on settings, configurations, and installs.
Try it for free now: http://bit.ly/DeepLearningContainer
If you have any issues or questions, feel free to reach out to me!
Excited to announce that my team at VITech (VITech Lab) has released our first free Deep Learning Container at AWS Marketplace - http://bit.ly/DeepLearningContainer
This is a fully pre-configured docker container with TensorFlow 2.0 and open-source libraries for Machine Learning, including Jupyter Lab & Notebook, Keras, Theano, PyTorch, OpenCV, H2O, CNTK, NVIDIA CUDA, cuDNN, Numpy, Scipy, scikit-learn, XGBoost, etc. Use the container to reduce the time and resources spent on settings, configurations, and installs.
Try it for free now: http://bit.ly/DeepLearningContainer
If you have any issues or questions, feel free to reach out to me!
The 2019 AI Index report
The AI Index Report from the HAI group at Stanford is a "starting point for informed conversations about the state of AI." The report is organized into 9 chapters that cover a variety of topics including things like Research and Development, Conferences, Technical Performance, The Economy, Education, Autonomous Systems, Public Perception, Societal Considerations, National Strategies and Global AI Vibrancy.
https://stanford.io/2s1wv9f
The AI Index Report from the HAI group at Stanford is a "starting point for informed conversations about the state of AI." The report is organized into 9 chapters that cover a variety of topics including things like Research and Development, Conferences, Technical Performance, The Economy, Education, Autonomous Systems, Public Perception, Societal Considerations, National Strategies and Global AI Vibrancy.
https://stanford.io/2s1wv9f
Stanford HAI
AI Index 2019
@catalyst_team are happy to announce the release of Catalyst v20.01.3, DL/RL framework for PyTorch
What is in Catalyst:
- Universal train/inference loop.
- Configuration files for model/data hyperparameters.
- Reproducibility - all source code and the environment will be saved.
- Callbacks - reusable train/inference pipeline parts.
- Training stages support.
- Easy customization.
- PyTorch best practices (Ranger optimizer, OneCycle, FP16 and more).
http://bit.ly/38RRevJ
What is in Catalyst:
- Universal train/inference loop.
- Configuration files for model/data hyperparameters.
- Reproducibility - all source code and the environment will be saved.
- Callbacks - reusable train/inference pipeline parts.
- Training stages support.
- Easy customization.
- PyTorch best practices (Ranger optimizer, OneCycle, FP16 and more).
http://bit.ly/38RRevJ
Self-Driving Research in Review: NeurIPS 2019
In this article, Peter Ondruska and Vladimir Iglovikov present an overview of the most relevant papers on self-driving technology from the Workshop on Machine Learning for Autonomous Driving and the NeurIPS conference.
http://bit.ly/36GQHLH
In this article, Peter Ondruska and Vladimir Iglovikov present an overview of the most relevant papers on self-driving technology from the Workshop on Machine Learning for Autonomous Driving and the NeurIPS conference.
http://bit.ly/36GQHLH
Exploratory Data Analysis for NLP: A Complete Guide to Python Tools
In this article, you will learn nearly all major techniques you can use to research your text data. It also includes a complete tour of Python tools that can help you get the job done.
http://bit.ly/31gdXyW
In this article, you will learn nearly all major techniques you can use to research your text data. It also includes a complete tour of Python tools that can help you get the job done.
http://bit.ly/31gdXyW
Introducing Label Studio, a swiss army knife of data labeling
In this article, you will learn about open-source data labeling, annotation, and exploration tool - Label Studio. Label Studio works with texts, images, audios, and HTML documents right out of the box.
http://bit.ly/2RQVBli
In this article, you will learn about open-source data labeling, annotation, and exploration tool - Label Studio. Label Studio works with texts, images, audios, and HTML documents right out of the box.
http://bit.ly/2RQVBli
12 февраля приглашаем всех на второй Open Data Science Meetup в Одессе. На нем вы познакомитесь с аугментацией и семантической сегментацией изображений, а также новыми ML сервисами от AWS.
Будет организована онлайн-трансляция.
Подробности и регистрация: http://bit.ly/31uOJx2
Будет организована онлайн-трансляция.
Подробности и регистрация: http://bit.ly/31uOJx2
Hey, I’d like to restart the digest with a new feature. Now, I can automatically share with you the most interesting links from my blog collection. Please vote for the links to help me pick the best blogs. To add the blogs, fill out the form: http://bit.ly/2IVGq54