NNI (Neural Network Intelligence) is a toolkit to help users run automated machine learning (AutoML) experiments. #automation #machinelearning parameters
https://github.com/Microsoft/nni

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv

With the plethora of Deep learning courses available on the internet, this (CS 598 LAZ: Cutting-Edge Trends in Deep Learning and Recognition) stands out as one of the best I have seen.

For instance, there 274 slides on meta-learning. (https://lnkd.in/enuZhAX).

https://lnkd.in/ehFAQew

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv

This person does not exist

By Philip Wang: https://lnkd.in/eEWxyYu

#GenerativeAdversarialNetworks #GAN

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv

Introducing a new blog (0:00-0:50) and then explaining what transfer learning is and why people have the wrong idea about it (0:50-03:05).

It's my first one of these, so go easy on me! <3

Cassie's blog: https://lnkd.in/e55m6sY (Start here: https://lnkd.in/eE4Vg6r)
Completely new to machine learning? Here's my intro: https://lnkd.in/eVuKzNe

Launchpad blog: https://lnkd.in/e3EW89u
Keeping up with AI: https://lnkd.in/ePqWvC3

View on YouTube: https://lnkd.in/eExmdET

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv

Quantum Machine Learning is not Machine Learning for Quantum Mechanics

There is a bit of confusion in the literature and research. Applying machine learning to resolve numerically accurate quantum mechanics applied to molecules does not constitute 'quantum machine learning' (QML). QML implies machine learning algorithms solved within a quantum mechanical computing device. Common misconception. Recent work does this error though work is very original applying Kernel methods in response properties.

#ai #quantumcomputing #machinelearning #datascience

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv

Hi

Highly recommended to see what is going on in these scientific Links ( Code, articles, summary , discussions .... )

AI Articles with Code ( most in Python )
https://www.paperswithcode.com/

Public summaries in Machine learning , organized with community ( Like stackoverflowin AI )
https://www.shortscience.org/?s=cs


Search /Filtering recent Arxiv ( pre print submissions ) ; Keep track of recent papers with sorting papers by similarity

http://www.arxiv-sanity.com



Latest Arxiv papers with abstract summary ! ( web interfece and python code )

https://github.com/chiphuyen/sotawhat
More info here :
https://huyenchip.com/2018/10/04/sotawhat.html


تشکر ویژه از دکتر حبیب‌زاده بابت به اشتراک گذاری منابع

@pytens

🤣😂
✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv

OpenAI built a text generator so good, it’s considered too dangerous to release https://buff.ly/2S61M1v #AI #ArtificialIntelligence #MachineLearning

How to Design a Neural Network for Image Classification

Here is a simple illustration of what a shallow and deep neural network looks like.

#DeepLearning #Fundamentals #neuralnetworks #design

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv

The AI Now Institute has published a report outlining the challenges of law enforcement using AI algorithms to help forecast criminal activity.

The research center based at New York University focuses on the social impact of AI. The paper shows the negative effects of relying on flawed data and focuses on thirteen case studies from different law enforcement agencies in the US.

For example, “dirty data” contains hidden biases that might predict that certain areas have elevated levels of crime. More police may be deployed in that area, leading to more racial profiling and arrests.

https://lnkd.in/dtx_2rg

#deeplearning #machinelearning #police #lawenforcement #algorithms

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv

There is the mathematical aspect to statistics - an important one - that can turn a lot of "normal" people off. But there is also applied statistics which, in John Tukey's words, lets us play in everyone's backyard.

Everyone, in this case, includes psychology, sociology, history, anthropology, physics, biology, economics, political science, and even art, literature, music and philosophy. Stats opens doors.

It can help us better understand the workings of the human mind, how societies and cultures function, how to interpret historical facts meaningfully and how think about the future.

One can learn a lot about human nature by studying a jobs or educational program, for example.

Most fundamentally perhaps, it shows us better ways to think about causation.

If a statistician only focuses on the math and programing, though, they will miss all of this. It seems a shame, but different strokes for different folks.

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv

MIT : Intro to Deep Learning
‏
First two 2019 lectures for MIT Intro to #DeepLearning now online!

Course schedule: https://lnkd.in/eDW7FTs
Lecture 1: https://lnkd.in/esDcMaP
Lecture 2: https://lnkd.in/epzKtXM

#artificialinteligence #machineleaning #neuralnetworks

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv

Accenture's 10 Essential ML Interview Questions (with Answers) by The Learning Machine!

https://www.thelearningmachine.ai/accenture

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv

Deep Convolutional Sum-Product Networks for Probabilistic Image Representations

Sum-Product Networks (SPNs) are hierarchical probabilistic graphical models capable of fast and exact inference.

Applications of SPNs to real-world data such as large image datasets has been fairly limited in previous literature. Here is a Convolutional Sum-Product Networks (ConvSPNs) which exploit the inherent structure of images in a way similar to deep convolutional neural networks, optionally with weight sharing.
#neuralnetworks #datasets #deeplearning

Paper: https://lnkd.in/ei4Gqjy

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv

🔥 Jupyter Notebook tip:
Need to share a code sample from your notebook?
1. Use the %pastebin magic function to select a range of cells ⚡️
2. Jupyter gives you a secret URL to share 🔗

Example: http://dpaste.com/3M6Y2A9 (expires in 7 days)

#python #datascience

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv

What is Reinforcement Learning?
Reinforcement Learning(RL): Type of machine learning technique that enables an agent to learn in an interactive environment by trial and error using feedback from its own actions and experiences.
Reinforcement learning uses rewards and punishment as signals for positive and negative behavior

Introduction to Reinforcement Learning: https://lnkd.in/gnywQgC

Build your own AI to play when you got on internet connection. The code is provided, try it yourself.

Article: https://lnkd.in/guARH7G
GitHub: https://lnkd.in/grkwSKs

#reinforcementlearning #machinelearning #deeplearning #python #keras #tensorflow

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv

What a last 12 months for #NLP! Here are 3 awesome in-depth articles to learn and implement the latest NLP libraries with their code:

Introduction to Flair for NLP: A Simple yet Powerful State-of-the-Art NLP Library - https://lnkd.in/ftFMuyR

Introduction to #StanfordNLP: An Incredible State-of-the-Art NLP Library for 53 Languages - https://lnkd.in/f2Tc2rV

Tutorial on #TextClassification (NLP) using #ULMFiT and #fastai Library in #Python - https://lnkd.in/f7bu8jM

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv

Aspiring data scientists often overlook learning discrete math, but they shouldn't.

There are a few key areas to study that that will really build your skills for data science:

1. Sets theory
2. Logic and Proofs
3. Combinatorics

👉 Why do you need to understand set theory, logic, and combinatorics for data science?

These areas of math are the basis for discrete probability and theoretical computer science, e.g. algorithms and data structures.

Don't expect to write good code if you don't understand algorithms and data structures, and don't expect to understand algorithms and data structures if you don't understand discrete math... (so study discrete math)

And really, if you've never studied logic, formally studying it will really help you be able to break problems down and solve them effectively as a data scientist.

So grab a book on discrete math, like this one, and starting working your way through the basics if you haven't already (chapters 0, 1, and 3 are most important).

👉 Download the free PDF -> https://lnkd.in/gNSJiYK

👉 Grab a copy from Amazon -> https://lnkd.in/gW_tVNf

#datascience #math #machinelearning

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv

AI For Everyone is almost here! In Week 1 of the course, you’ll learn everything from what a neural network is to how you acquire data.

Here’s what else you’ll learn:

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv

There are three main kinds of #machinelearning used in AI: unsupervised learning, supervised learning and reinforcement learning.

Daily #datascience - at least my corner of it - is mainly concerned with the first two. #ReinforcementLearning is probably closest to what most people probably think of when they hear "AI" and the overused "learning from data."

Besides the venerable #ArtificialIntelligence (Russell and Norvig), three books that cover reinforcement learning in detail are:

- Reinforcement Learning: State-of-the Art (Wiering and van Otterlo)
- Reinforcement Learning: An Introduction (Sutton and Barto)
- Decision Making Under Uncertainty (Kochenderfer et al.)

The connection between AI and human psychology can be stretched, but there is one, and I've found these (among others) helpful:

- Cognitive Psychology (Sternberg and Sternberg)
- An Introduction to Decision Theory (Peterson)
- Algorithms to Live By (Christian and Griffiths)
- Simple Heuristics That Make Us Smart (Gigerenzer et al.)

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv

Here are the COMPLETE Lecture notes on Professor Andrew Ng's


Stanford Machine Learning Lecture: https://lnkd.in/gR5sRHg

#lecturing #machinelearning #beginner #artificialintellegence #fundamentals #artificailintelligence #neuralnetwork #repository #datascientists #computervision #neuralnetworks

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv