Learn probabilistic programming with TensorFlow Probability, from the ground up. The Bayesian Methods for Hackers book is now available in open source in TFP! Read post here ↓

Link Review


❇️ @AI_Python
🗣 @AI_Python_Arxiv
✴️ @AI_Python_EN

30 Free Courses in #NeuralNetworks, #MachineLearning, #Algorithms, and #AI — https://bit.ly/2p7zQMB #abdsc #BigData #DataScience #DeepLearning #DataScientists

❇️ @AI_Python
🗣 @AI_Python_Arxiv
✴️ @AI_Python_EN

The Athlete and the Machine: New Trends in #AI and Sports Technology https://buff.ly/2MJzIiG #MachineLearning

❇️ @AI_Python
🗣 @AI_Python_Arxiv
✴️ @AI_Python_EN

Exciting news from #NeurIPS – the European Laboratory for Learning and Intelligent Systems (ELLIS) has been announced! The centre will support research and help industry leverage #AI.

https://nvda.ws/2roKRfK

❇️ @AI_Python
🗣 @AI_Python_Arxiv
✴️ @AI_Python_EN

The Nytimes Data Science Group is searching for multiple full-time data scientists with a focus on machine learning. This is a great group of people working on interesting and important problems.

More info: https://nytimes.wd5.myworkdayjobs.com/en-US/DataInsights/job/New-York-NY/Data-Scientist--machine-learning-_REQ-004142

❇️ @AI_Python
🗣 @AI_Python_Arxiv
✴️ @AI_Python_EN

😁
❇️ @AI_Python
🗣 @AI_Python_Arxiv
✴️ @AI_Python_EN

Excited to present practical fairness paper "Why is My Classifier Discriminatory?" at #NeurIPS2018

papers.nips.cc/paper/7613-why-is-my-classifier-discriminatory

❇️ @AI_Python
🗣 @AI_Python_Arxiv
✴️ @AI_Python_EN

NeurIPS 2018 video talk collection #NeurIPS2018

https://buff.ly/2EaUFBC

❇️ @AI_Python
🗣 @AI_Python_Arxiv
✴️ @AI_Python_EN

👉 If you like our channel, i invite you to share it with your friends:
Our channel in english: ✴️ @AI_Python_EN
Our Daily arXiv Channel: 🗣 @AI_Python_Arxiv

BTW: Thank you for joining :)

Very comprehensive article on transfer learning. It covers the theory behind transfer learning in general and then how it can be used for deep learning. He then also presented two hands-on case studies where he used transfer learning in a CV classification task for first a binary class problem and then second multi-label classes. Code is also provided using Keras with the TensorFlow backend. Definitely check this article out. Transfer learning has a high practical importance for machine learning practitioners.
#deeplearning #machinelearning

Article: https://lnkd.in/daa6_UB
Github: https://lnkd.in/dhxXcRg

❇️ @AI_Python
🗣 @AI_Python_Arxiv
✴️ @AI_Python_EN

Papers with Code: https://paperswithcode.com

#ArtificialIntelligence #DeepLearning #MachineLearning #NeuralNetworks #Technology


❇️ @AI_Python
🗣 @AI_Python_Arxiv
✴️ @AI_Python_EN

PracticalAI: A practical approach to learning machine learning

By Goku Mohandas: https://lnkd.in/eyFbdCC

#machinelearning #naturallanguageprocessing #jupyter #python #pytorch


❇️ @AI_Python
🗣 @AI_Python_Arxiv
✴️ @AI_Python_EN

Comixify: Transform video into a comics. They used a 2-stage approach: (a) frame selection and (b) style transfer. The results look pretty cool!

paper: https://lnkd.in/eszcexU
demo: https://lnkd.in/edrtfPd
test video: https://lnkd.in/ebWpPRD

❇️ @AI_Python
🗣 @AI_Python_Arxiv
✴️ @AI_Python_EN

The AI art gallery from NeurIPS Creativity workshop

AI Art Gallery: http://aiartonline.com

#NeurIPS2018

❇️ @AI_Python
🗣 @AI_Python_Arxiv
✴️ @AI_Python_EN

My 13-minute oral presentation at hashtag#NeurIPS2018 summarizing our world models paper. I felt like the weight of the world (model) was finally lifted off my shoulders after giving the talk.

article → https://lnkd.in/fa36JNH
paper → https://lnkd.in/gPjH_NJ


❇️ @AI_Python
🗣 @AI_Python_Arxiv
✴️ @AI_Python_EN

A Programmer’s Introduction to Mathematics. It teaches someone with programming knowledge and experience how to engage with mathematics. Achieve this goal largely because of the implicit overlap in the content and ways of thinking between math and programming.
Until now. If you’re a programmer who wants to really grok math, this book is for you.
GitHub: Link
#Book #کتاب

Download :
https://t.me/ai_python_en/190

❇️ @AI_Python
🗣 @AI_Python_Arxiv
✴️ @AI_Python_EN

Dr. Jeremy Kun:

A Programmer’s Introduction to Mathematics.

❇️ @AI_Python
🗣 @AI_Python_Arxiv
✴️ @AI_Python_EN

Computer Vision problems are often solved using a Machine Learning approach. In Machine Learning, we learn from data.

What if you do not have enough data? Well, there is still some hope.

If you are able to segment your shape out, you can use Hu Moments for shape matching. These moments are invariant to translation, scale, and rotation and can identify the shape even if it has undergone those transformations.

You will learn about raw moments, central moments and Hu moments in our post today.

We also show how to use moments for matching shapes.

As always, we are sharing code in C++ and Python.

https://lnkd.in/eVk_J5M

#AI #MachineLearning #ComputerVision #OpenCV


❇️ @AI_Python
🗣 @AI_Python_Arxiv
✴️ @AI_Python_EN

How do I get a job in machine learning?

I get asked this question almost daily.

The short answer is "there's no one set path."

But this could fit with anything. And it isn't really helpful.

Here's what I would do if I was fired tomorrow.

💡1. Get really good at whatever it is I decide to do (I'm working on this anyway)

Whatever field you want to get into, #machinelearning, #datascience, health, media, this is a given. You have to be good at what you do.

Not the best at one thing?

That's okay. Combine it with something else and become the best at the crossover.

❇️ @AI_Python
🗣 @AI_Python_Arxiv
✴️ @AI_Python_EN

For me, my #coding skills were lacking, so I made it up for it through several different forms of communication (see point 2).

🎤2. Communicate whatever it is I'm good at in a way people can understand

If you can #code but can't write practice writing.

I can't count the number of times I've found some brilliant code online but struggled to understand it because it hadn't been documented well.

Got a project you've worked on? (you should)

Share it. And share your thought process around each step. Why did you do that thing in part 3?
It's the Winston Churchill approach. He wasn't anywhere near the most qualified person for the role of Prime Minister. But he was the best at communicating what he knew. Because of this, the people put their trust in him. Then he backed it up by being good at what he did.

📝3. Apply relentlessly

If I wasn't getting rejected once per week, I'd start applying more. And not just with a resumé.
Someone told me their resumé gets filtered. I'm not sure what a resumé filter is but I'd find a way to get around it.
Plus, I'm not interested in somewhere that hires solely off the basis of an A4 sheet of paper.
I'd go out of my way to find who the best person would be to talk to. And then I'd find a problem they're having and fix it.
Will this work?
There's no guarantees. There's never a guarantee.
But what's the alternative?
To not be good at what you do?
Or to not communicate your skillset?
Or to not find the right person to talk to?
You already know the answer to these.

❇️ @AI_Python
🗣 @AI_Python_Arxiv
✴️ @AI_Python_EN

The Neural Aesthetic

Notes and around 30 hours of video lectures are up here, by Gene Kogan: https://lnkd.in/dCMpmGx

Big map of all the slides: https://lnkd.in/dB8yJtp

#artificialintelligence #deeplearning #generativemodel #machinelearning #reinforcementlearning


❇️ @AI_Python
🗣 @AI_Python_Arxiv
✴️ @AI_Python_EN

"A Brief Survey of Deep Reinforcement Learning"

Arulkumaran et al.: https://lnkd.in/dwt_--X

#100DaysOfMLCode #ArtificialIntelligence #DeepLearning #MachineLearning #NeuralNetworks #ReinforcementLearning

❇️ @AI_Python
🗣 @AI_Python_Arxiv
✴️ @AI_Python_EN