How Machine Learning and AI are Changing eSports and Knowledge Itself
#Automation #AI #MachineLearning https://medium.com/swlh/how-machine-learning-and-ai-are-changing-esports-and-knowledge-itself-b4d977473cc1?source=rss-------8-----------------artificial_intelligence

I may be wrong, but I get the impression that some data science people believe regression comes in just two flavors - OLS linear and binary logistic.

Setting aside the relationship between neural nets and regression, and that VAR, GARCH, Structural Equation Models and numerous other statistical models are really forms of regression, I have no idea how many kinds of "regression" are in common use.

"Dozens" would probably be an underestimate. There are countless other types which are used infrequently but essential in certain circumstances, like a fifth pitch in baseball.

Moreover, there is usually more than one way to estimate most statistical models. It's not unusual for a statistician to run one kind of regression model several ways with maximum likelihood estimation (MLE) and Bayesian alternatives, for example.

We have a BIG regression decision tree, and our choices are seldom inconsequential.

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv

You know what a neural network is, and you know what a ML project workflow looks like. Now how do you implement it throughout your entire company? Week 3 of AI for Everyone will walk you through it:

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv

Left: how you would plot the Xception architecture in a paper.
Right: how you would implement it with the Functional API (that's the entire code).

1:1 match between how you think about it and how you write it.

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv

How does Google Translate's AI work? https://youtu.be/sIoHFPGOY0I

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv

Lingvo is a deep learning framework used for sequence modeling tasks like machine translation, speech recognition, and speech synthesis. Learn more here ↓
https://medium.com/tensorflow/lingvo-a-tensorflow-framework-for-sequence-modeling-8b1d6ffba5bb?linkId=63952201

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv

There are links to lots of AI ethics resources & articles in this post: "In Favor of Developing Ethical Best Practices in AI Research"
https://ai.stanford.edu/blog/ethical_best_practices/
✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv

Using supervised Machine Learning to reach a desired solution #MachineLearning #deeplearning #ArtificialIntelligence #AI #TechNews #technology #deeptech
http://www.intelligentcio.com/eu/2019/02/26/using-supervised-machine-learning-to-reach-a-desired-solution/

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv

Lambda GPU computers power Deep Learning research at Apple, Microsoft, MIT, and Stanford. Learn more here: http://LAMBDALABS.COM

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv

Introduction to Deep Learning
Slides, course materials, demos, and implementations
https://chokkan.github.io/deeplearning/

ISSCC2018 - 50 Years of Computer Architecture:From Mainframe CPUs to Neural-Network TPUs


https://www.youtube.com/watch?v=NZS2TtWcutc

Theorizing from Data by Peter Norvig (Video Lecture)

https://catonmat.net/theorizing-from-data-by-peter-norvig-video-lecture

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv

Introducing TensorFlow Datasets

By TensorFlow: https://lnkd.in/d2yEjSr

#MachineLearning #Data #Dataset #TensorFlow

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv

6 Tips to Improve Your Code for Data Science (with links)

1. Strictly follow style standards
-> https://lnkd.in/gKZUjVa

2. Use a linter to enforce style standards
-> https://lnkd.in/d_prybR

3. Write modular, generic, object-oriented code -
-> https://lnkd.in/gsynW6Q
-> https://lnkd.in/dx53u53

4. Write unit tests to test your functions and methods
-> https://lnkd.in/dsy-bPu

5. Organize your code base
-> https://lnkd.in/dviGffH

6. Separate exploration and production development, and develop production code using test-driven development (TDD)
-> https://lnkd.in/dMn-s32


If you'd like some real code examples, I've got 5 end-to-end data science projects with instructions, data, code, and complete video walkthroughs as part of the DSDJ course.

These examples and videos will walk you through everything that you need to take your data science coding skills to the next level.

To learn more, join our mail list today at https://lnkd.in/g7AYg72

#datascience #programming

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv

TensorBoard now works in Jupyter Notebooks, via magic commands "%" that match the command line.

Example: https://lnkd.in/dfGH2gH

H / T : Josh Gordon

#artificialintelligence #deeplearning #tensorflow

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv

Visualizations are one of the best ways of telling a story with data. They are extremely useful when trying to understand data and unearth hidden patterns. Check out these 4 articles to design mind-blowing visualizations:

A Collection of 10 Data Visualizations You Must See - https://lnkd.in/fRemdbn

How to create Beautiful, Interactive data visualizations using Plotly in #R and #Python - https://lnkd.in/fN3e9m8

Comprehensive Guide to #DataVisualization in R - https://lnkd.in/fw9M-De

R-analyst #Cheatsheet: Data Visualization in R - https://lnkd.in/fnakeqH

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv

Data scientists didn’t invent imposter syndrome, but we’re really good at it. Vagueness of what a data scientist does is a big contributor. My co-authors and I tried to clarify.
https://lnkd.in/e9M2v-X

Here's a blog post building on it.
https://lnkd.in/eDAUy4a

Also, here’s an imposter syndrome pep talk especially for data scientists. I hope it helps.
https://lnkd.in/drv-hfX

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv

What skills should you start learning to become a data scientist?

I've had a lot of people ask me that recently, but it's really the wrong question.

Try this instead -

➡️ 1. Choose a problem (and dataset) that you find interesting
➡️ 2. Begin trying to solve the problem
➡️ 3. When you get stuck because your skill set is limited, go learn that skill

For example, if you get stuck...
- loading the data into a dataframe/table, then learn pandas or SQL
- identifying outliers, then study stats
- figuring out what to do with missing data, then learn when to remove data, replace values, impute values, etc
- building a regression model that makes good predictions, then learn about regression techniques

👉 There are 2 big differences when you take this approach:

1. You don't waste time guessing what you need to know
2. You're highly motivated to learn at every step of the way

This eliminates the scenario where you're learning a subject because someone else told you it's a good idea.

👉 Now you're learning because you NEED that knowledge for something useful.

Start using this approach in your studies and you'll also see that you're learning more quickly and completely.

#datascience #aspiring #datascientist

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv

PyTorch under the hood

By Christian S. Perone: https://lnkd.in/diyNcYU

#artificialintelligence #deeplearning #pytorch

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv

Best article I've read so far on understanding how Neural ODEs work. Well and clearly explained by solving a regression problem. If you have read the paper (Link: https://lnkd.in/dfDnJJz) and had difficulties understanding it then you should definitely read this blog post. #deeplearning #machinelearning

Link: https://lnkd.in/dhMhwyb

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv

The Matrix Calculus You Need For Deep Learning

By Terence Parr and Jeremy Howard : https://lnkd.in/dC5MqZM

#ArtificialIntelligence #BigData #DeepLearning #MachineLearning #NeuralNetworks

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv