talk at PyData Amsterdam 2019 on our low-to-high resolution project is out! If you missed his talk at PyData Amsterdam or in general if you're interested in image super resolution, check out his video and also of course our Github repo for more information. #deeplearning #machinelearning #AxelSpringerAI

▶️ YouTube Video: https://lnkd.in/d6YHaFS
🔤 Code: https://lnkd.in/dkJUaQe

✴️ @AI_Python_EN

Quick links for all things #R and #Python:

1. Overview of using python with RStudio: https://lnkd.in/d5NkJAt
2. Python & #shiny: https://lnkd.in/dVfkE6b
3. Python & #rmarkdown: https://lnkd.in/dXpSd7i
4. Python with #plumber: https://lnkd.in/dn2pEAQ

For a central location to publish all of your team's data products (R artifacts, R & python mixed assets, and #jupyternotebooks), check out RStudio Connect: https://lnkd.in/dXW7iPG

✴️ @AI_Python_EN

Human in the Loop: Deep Learning without Wasteful Labelling

Kirsch et al.: https://lnkd.in/eP323W3

Code: https://lnkd.in/e7-wbxD

#activelearning #deeplearning #informationtheory
#machinelearning

✴️ @AI_Python_EN

The same statistical or machine learning method can be programmed (implemented) in different ways, and this can have an impact on the results. (I'm not referring to programing errors.)

Moreover, the initial start seed can strongly affect a routine - change the start seed and the results may vary substantially.

So, the same method programmed the same way may give different results on the same data if you change the start seed.

Most (hopefully all) statisticians are aware of this, but I suspect most users (e.g., decision makers) are not. "AI" is not immune to this.

✴️ @AI_Python_EN

TensorFlow 2.0 Beta has just been released!! This time, I am a big fan. The new version is so good, so easy & intuitive, and game changing compared to the previous TensorFlow 1 versions. It has such massive value that I decided to make a huge course on TensorFlow 2.0, covering most of the useful models in Deep Learning and Artificial Intelligence. Seriously this is one of the most complete guides I’ve ever made: inside we implement ANNs, CNNs, RNNs, Deep Q-Learning, Transfer Learning, Fine Tuning, APIs for Mobile Apps, Computer Vision, Deep NLP, Data Validation, TensorFlow Extended and even Distributed Training handling multiple GPUs, all that in TensorFlow 2.0!

And that’s not all, during these first 72 hours you get three amazing Bonuses, including the highly demanded Yolo v3, one of the most powerful models in Computer Vision.

Link here:
https://lnkd.in/gBtZuMN

#machinelearning #deeplearning, #artificialintelligence #computervision #nlp #completeguide
✴️ @AI_Python_EN

Another lovely development in #Healthcare #DeepLearning

Building a Benchmark Dataset and Classifiers for Sentence-Level Findings in AP Chest X-rays.

#datasets
Arxiv: https://lnkd.in/dxx5iCY

✴️ @AI_Python_EN

"Endlessly Generating Increasingly Complex and Diverse Learning Environments and their Solutions through the Paired Open-Ended Trailblazer (POET)"

Slides by Jeff Clune: https://lnkd.in/ePpcNQS

#neuroevolution #evolutionstrategy #machinelearning

✴️ @AI_Python_EN

A deep learning model developed by NVIDIA Research turns rough doodles into highly realistic scenes using generative adversarial networks (GANs). Dubbed GauGAN, the tool is like a smart paintbrush, converting segmentation maps into lifelike images.

#GAN #deeplearning

✴️ @AI_Python_EN

When the paper you’re reading keeps citing another paper.

#deeplearning #jokes
✴️ @AI_Python_EN

Generative adversarial networks for text generation: non-RL methods
https://medium.com/@karthik.chintapalli/generative-adversarial-networks-for-text-generation-part-3-non-rl-methods-70d1be02350b
#NLP

✴️ @AI_Python_EN

Lesson 5: Deep Dream implementation using Swift for #TensorFlow.

Colab: https://colab.research.google.com/github/zaidalyafeai/Swift4TF/blob/master/Swift4TF_DeepDream.ipynb …

✴️ @AI_Python_EN

Purdue University researchers have used #AI and engineered flying #Robots that behave like hummingbirds!

arXiv: Flappy Hummingbird: An Open Source Dynamic Simulation of Flapping Wing Robots and Animals

https://github.com/purdue-biorobotics/flappy

✴️ @AI_Python_EN

I try to make the interview a fun moment for programmers.
https://lnkd.in/dJJbFbE

OpenAI's MuseNet Learned to Compose Mozart, Bon Jovi and More

article : https://openai.com/blog/musenet/
video : https://www.youtube.com/watch?v=pQA8Wzt8wdw

article on Machine learning got published in Better Programming on Medium
https://medium.com/better-programming/from-machine-learning-to-reinforcement-learning-mastery-47f33d9f6b41

Feedback welcome!

✴️ @AI_Python_EN

"What Does BERT Look At? An Analysis of BERT's Attention"
https://arxiv.org/abs/1906.04341

✴️ @AI_Python_EN

New feature in Habitat-API: tensorboard integration and video generation: watch videos of your agents at various points in training. Courtesy: Jason Jiazhi Zhang.
https://github.com/facebookresearch/habitat-api/pull/127

✴️ @AI_Python_EN

APS Physics Viewpoint on 4 independent works on Neural Network Variational Methods for Open Quantum Systems!
https://physics.aps.org/articles/v12/74

✴️ @AI_Python_EN

Convolutional #NeuralNetworks (CNN) for Image Classification — a step by step illustrated tutorial: https://dy.si/hMqCH
BigData #AI #MachineLearning #ComputerVision #DataScientists #DataScience #DeepLearning #Algorithms

✴️ @AI_Python_EN

Modern machine learning is driven by building good environments/datasets. We’ve just open-sourced a tool we created for rendering high-quality synthetic robotics data:
OpenAI : We're releasing ORRB (OpenAI Remote Rendering Backend)—a Unity3d-based system that enables rapid and customizable renderings of robotics environments.
Paper: https://arxiv.org/abs/1906.11633
Code: https://github.com/openai/orrb

✴️ @AI_Python_EN

#Python, Performance, and GPUs

https://towardsdatascience.com/python-performance-and-gpus-1be860ffd58d

✴️ @AI_Python_EN