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

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