This part only provides a quick glance at some important features in Python 3. If you're interested in all of the most important features, please read the official document, What’s New in #Python .

Github Link - https://lnkd.in/ftcp5jQ

#python #datascience #machinelearning #dataanalysis

✴️ @AI_Python_EN

Amazon Comprehend Medical – Natural Language Processing for Healthcare Customers | Amazon Web Services https://amzn.to/2QJLS0W #AI #DeepLearning #MachineLearning #DataScience

✴️ @AI_Python_EN

No matter how great we think the AI, ML, DL algorithms we created are, nothing beats a human-made being!

The future lies in cobots with human-made intelligence running the world and AI as a tool.

Make friends, build a family, use AI as a tool to make your life better at work and turn it off when you can!

#algorithms #ai #machinelearning

✴️ @AI_Python_EN

Bio-LSTM: A Biomechanically Inspired Recurrent Neural Network for 3D Pedestrian Pose and Gait Prediction #DataScience #MachineLearning #ArtificialIntelligence http://bit.ly/2XPR979

✴️ @AI_Python_EN

Useful post to generate images by means a Generative Adversarial Networks (#GANs).

This is an unsupervised learning problem combining game theory and #ReinforcementLearning.

You will learn in the post from basics of GANs to implementation of the model in #TensorFlow.

Post: https://lnkd.in/dcRJp-8

Github: https://lnkd.in/d2yu-t9

If You Like Our Channel,invite your friends and share it

✴️ @AI_Python_EN

This article summarizes and explains some of the most frequently used algorithms in NLP
https://medium.com/@ODSC/essential-nlp-tools-code-and-tips-39b7b2b7d7ba

✴️ @AI_Python_EN

Step 1: pip install ludwig
Step 2: Download a csv dataset
Step 3: Create a model definition yaml file to specify input and output features
Step 4: Run ludwig experiment --data_csv path_to_csv --model_definition_file model_definition.yaml
Step 5: Receive a high accuracy model for rating a clothing item from a Kaggle dataset or any other dataset
Step 6: WOW! This is almost like making noodles in 2 minutes!

A few years ago, when I helped establish a new HP office in Braunschweig, Germany for a newly acquired team, it was a building located on a street called Ludwig Strasse and my German GPS confused me so much that I wished I had a self driving German car to locate this building :) BTW, almost every other street in Germany is named Ludwig something, right Simon Winkelbach ? :)

Curiosly enough, Uber names its self-driving deep learning model design framework Ludwig and I am immediately reminded of LudwigStrasse in Braunschweig. I decided to give this Uber Ludwig a self-driving spin and it reminded me of Microsoft AzureML studio (which is a more visual design framework of course)
https://lnkd.in/gijwygv

#deeplearning
#kaggle

✴️ @AI_Python_EN

Very nice blog post by John Langford on code submission policy https://lnkd.in/exAi6Cw. I agree with many of John's points. This is pretty much what Kamalika Chaudhuri and I are trying to accomplish this year at ICML by introducing optional supplementary code submission: https://lnkd.in/eFfTTQK


✴️ @AI_Python_EN

In #NLP, completed different text preprocessings in Spacy and NLTK, diffrent types of word and sentence vectorizations, and re library.

Now yet to do document and sentence classification and clustering.

✴️ @AI_Python_EN

A thread on data science generalists-vs-specialists.

Takeaways:
1) You don't have to know everything.
2) It's OK to specialize in an area you love.
3) Saying "I only build models" is the moral equivalent of licking the frosting off all the cupcakes.

https://lnkd.in/eAHQavr

✴️ @AI_Python_EN

Alex Smola is freely publishing his 639-pages long PDF book on Deep Learning. An absolute marvel which would be a great companion to my own upcoming book www.interviews.ai

http://d2l.ai/

✴️ @AI_Python_EN

Data Science with R Cognitive Classes

DO NOT SKIP THE LAB EXERCISE. IT IS VERY HELPFUL

Here is the sequence we should follow -

R101
https://lnkd.in/fXTKq5U

Using R with Databases
https://lnkd.in/fRrBV7N

Data Visualization with R
https://lnkd.in/fWT8ZVK

Machine Learning with R
https://lnkd.in/fERn7eT

Data Analysis with R is coming soon on Cognitive.
Here is the link
https://lnkd.in/fm-BSaS

#dataanalysis #datavisualization #datascience #machinelearning

✴️ @AI_Python_EN

Self Attention GAN is a image generative model which published in 2018. My project aims to generate high resolution and vivid Hearthstone cards using PyTorch. Self attention map and model training details have been visualised in tensor-board.

Repository: https://lnkd.in/fA4uMYZ
Paper: https://lnkd.in/ff6pnuj

#AI #deeplearning #GAN
#computervision

✴️ @AI_Python_EN

Data Science Lifecycle



by Global Tech Council #datascience

✴️ @AI_Python_EN

If you’re learning #datascience or #analytics, then really take the time to understand the art of making the complex simple.

No matter where you go, the data that you use for your:
- visualizations
- machine learning
- statistical analysis
- presentations

All boils down to how well you can communicate the results.

So build the habit on documentation, storytelling, and simplifying your thoughts on papers.

Spend that extra time to articulate your thoughts and think deeply on how you want to present your data.

Because that’s a skill that will always be needed in any place you go.

And not only will you thank yourself for doing this in the future, but your team will love you for making it so simple for them. 🙂

Also, who doesn’t love a simple and meaningful story.

#machinelearning #storytelling #communication

✴️ @AI_Python_EN

https://lnkd.in/edT8m4y #machineleaning
“PyText is a deep-learning based NLP modeling framework built on PyTorch”

For those unfamiliar with the man: Schmidhuber is one of the creators of LSTM. Well worth your time.
https://lnkd.in/dYgXxMm

✴️ @AI_Python_EN

Machine learning models are being increasingly used to make decisions that affect people’s lives. With this power comes a responsibility to ensure that the model predictions are fair and not discriminating.

#machinelearning #bias
https://towardsdatascience.com/is-your-machine-learning-model-biased-94f9ee176b67?gi=d3c7b468df95

✴️ @AI_Python_EN

Check out this beautifully drawn notes from the excellent Coursera specialization by Andrew Ng!

Source: https://lnkd.in/dw5_Fmm

✴️ @AI_Python_EN

▪️Data Science Projects:

☆ The Data Science IPython Notebooks:
=> This repository is filled with IPython notebooks that cover different topics, going from Kaggle competitions to big data and deep learning.
[ https://lnkd.in/dW3WBi6 ]

☆ The Pattern Classification:
=> Tutorials and examples to solve and understand machine learning and pattern classification tasks.
[ https://lnkd.in/d9PGxHm ]

☆ Deep Learning In Python:
=> This repository is the way to go!
[ https://lnkd.in/d-hNVCD ]

More ...
▪️Data Science News
▪️Data Science Books
▪️Data Science Talks
▪️R for Data Science Talks
▪️Python for Data Science Talks
▪️Big Data Talks
▪️Data Science Podcasts
▪️Data Science Webinars
▪️Data Science Tutorials
▪️Data Science Community
▪️Data Science Courses

Refer to the full article
[ https://lnkd.in/dmKmx_D ]

✴️ @AI_Python_EN

Although there have been notable exceptions, quantitative marketing research on the whole has historically been quite basic.

In some respects, MR is still living in the early 90s, just before data warehousing, data mining and predictive analytics began to boom - developments that largely bypassed or were ignored by MR.

Though AI, machine learning, automation, etc., are now the buzz in MR, many marketing researchers are struggling to adapt the new world of marketing and marketing analytics.

52 Things About Customer Analytics (Sherman and Sherman) is a good place to start if you'd like to learn more about some of these new developments. Data Mining Techniques (Linoff and Berry) and Introduction to Algorithmic Marketing (Katsov) delve into these and related topics in more detail.

Data Science and Advanced Analytics aren't for everyone, though, and we need to bear this in mind. Many marketing researchers who have leaned on selling and people skills over the years are going to find the road ahead very bumpy. More and more, you have to be able to walk the walk if want to talk the talk.

✴️ @AI_Python_EN

DeepMind and Google: the battle to control artificial intelligence

Blog by Hal Hodson: https://lnkd.in/eVYhX2e

#artificialintelligence #deeplearning #reinforcementlearning

✴️ @AI_Python_EN