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

Ever wondered what a person's real age was? Or have you seen a baby and been really confused if it is a boy or a girl? Well, guess what! LearnOpenCV has a new blog post by Vikas Gupta and it reveals how you can easily guess age and gender using OpenCV Deep Learning

https://lnkd.in/dwsPtVQ

We'll be using Convolutional Neural Network (CNN) architecture, and focus on honing the Age Prediction Model.

Like, tag your friends and follow us for more of such exciting stuff! Mention reviews and what you want us to work on next, in the comments!

#LearnOpenCV #OpenCV #MachineLearning #DeepLearning #AI #ComputerVision #ImageRecognition #GenderClassification #AgeClassification #Python #Cplusplus

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv

Getting started with #datascience and #machinelearning? Don't miss out on these 5 incredible articles covering various #ML algorithms (+ code) every beginner must know:

6 Easy Steps to Learn #NaiveBayes #Algorithm (with codes in #Python and #R) - https://lnkd.in/fVz5sS5

Introduction to k-Nearest Neighbors: Simplified - https://lnkd.in/fghna-N

Understanding Support Vector Machine algorithm from examples - https://lnkd.in/fW8AhpS

A comprehensive beginner’s guide to create a Time Series Forecast - https://lnkd.in/f7ZAVPE

Essentials of Machine Learning Algorithms -
https://lnkd.in/fdEGhjf

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv

Very cool generating beautiful LaTeX plots for neural networks with PlotNeuralNet. A Python interface is also available as well as some examples (VGG-16, UNet etc). Check it out! #deeplearning #machinelearning

Github: https://lnkd.in/dtAiTCE

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv

Jeremy Howard

Introducing fastec2: AWS computer management for regular folks I wrote this to make my life easier. Hopefully it helps you too... :)

https://www.fast.ai/2019/02/15/fastec2/

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv

Artificial Intelligence, the History and Future - with Chris Bishop
https://www.youtube.com/watch?v=8FHBh_OmdsM

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv

Editing photos of faces using basic sketches, and letting a GAN do the rest. Lets you add/change: earrings, glasses, hair style, dimples, & more.

Paper: https://arxiv.org/pdf/1902.06838.pdf

Code: https://github.com/JoYoungjoo/SC-FEGAN

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv

Deep Learning ☹️☹️
#Fun

〰️〰️〰️〰️〰️
©️ @Code_Community

With packages like caret and sci-kit-learn, the implementation of machine learning algorithms is quite easy. The most challenging part of machine learning is to understand the underlying model metrics, parameter tuning conditions and choosing the right model evaluation metrics.

For example, If you're working on a regression problem, metrics like MSPE, MAPE, R-square, and Adj. R-square is valued more than accuracy per se. In the case of the classification problem, metrics like Precision-Recall, ROC-AUC, Accuracy, and Log-loss play a vital role.

Choosing the right parameters/metrics to create and evaluate models is the most important of machine learning implementation than just using a package or function is to create a model with no intent. The capability as mentioned earlier requires a lot of hands-on experience, domain knowledge, and research.

Are you evaluating your models effectively?

Share your thoughts and insights with the community in the comments below.


✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv

"For many companies, deploying AI is slower and more expensive than it might seem."

Recent article in MIT Technology Review.

https://www.technologyreview.com/s/612897/this-is-why-ai-has-yet-to-reshape-most-businesses/

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv

Download this very useful Infographic - it includes a step-by step process of cleaning text data in python using a Twitter case study. #Python

@AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv

How deep learning is being used by a Canadian dairy farmer, a Kenyan microbiologist, a 73-year old starting a second career, an Australian accountant expanding use of solar power, a son of refugees in cybersecurity, & a cancer genomics researcher:
https://www.fast.ai/2019/02/21/dl-projects/

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv

9 YouTube Channels That Will Teach You Everything You Need to Know About #artificialintelligence

🌎 Link

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv

In time-series analysis, a good-fitting and reasonable model may actually be misleading.

It's usually wise to test for "regime switching" since different processes (models) may be operating in different sections of the data series.

This is not merely a geeky issue and is very important in fields such as marketing, where consumer behavior and responses to marketing can change over time, sometimes suddenly.

In cross-sectional data analysis as well we must be careful about total sample models, since segments of consumers, some hidden, can react differently to new products and other marketing activity.

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv

Innovation Nation: AI godfathers gave Canada an early edge — but we could end up being left in the dust

"Canada is hanging on to the lead by 'our fingernails' as the gold rush to commercialize artificial intelligence goes global"

By James McLeod: https://lnkd.in/emxjPNS

#artificialintelligence #business #deeplearning

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv

Week 2 of AI for Everyone is all about identifying and building AI projects. Check out what you’ll learn:

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv

In the context of algorithm fairness in AI. From the O'Reilly Data Show podcast, Sharad Goel says: "You need domain expertise. There's no silver bullet. There's no black box you stick your algorithm into and it gives you thumbs up or down. It always depends on domain and context".

Examples in the podcast and paper are from loan approvals and the elusive idea of "fairness".

It's encouraging that people are socializing the challenges and limitations of data driven approaches and the role domain context plays in it.

This also has ramifications for organizations trying to create effective analytics strategies: it's hard delegate analytics because the needed domain context originates outside of the analytics space (which also explains why outsourcing analytics/data science offshore has not been successful).

Finally, on the idea of fairness, it's worth pointing out this is a bit if old news. Thomas Lumley points out in a similar article "This is old news in medical diagnostics, but appears not to have been considered in some other areas".

O'Reilly Data Show - O'Reilly Media Podcast -
https://lnkd.in/e9ryTZc

#analytics #datascience #machinelearning #statistics

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv

💡 What is multi-armed bandit testing and why is it useful?

Multi-armed bandit (or simply "bandit") testing is similar to multivariate and A/B testing, but the sampling distribution for variants change gradually over time as feedback is received.

For example, with traditional A/B tests, we could test 2 email subject lines: A and B. We would initially send out emails to 200 customers, sending 100 A variations and 100 B variations. After some set period of time, say 24 hours, we would observe which email variant was opened by more customers. We would then send that variant to all customers moving forward.

With bandit testing, we would set some learning rate for the distribution of variants to change over time. Perhaps 60 customers opened the A variant emails and only 50 customers opened the B variant emails. We could then shift the distribution from (50% A, 50% B) to (55% A, 45% B) for the next round of emails.

Using this approach, we can continuously monitor the response from our audience and shift our actions accordingly. This is particularly useful in marketing or any industry where people's preferences and opinions may change rapidly since it continuously tests and learns preferences and can adapt very quickly.

#datascience #dsdj #multiarmedbandit
#QandA

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv