Data science is an ever-evolving field. As data scientists, we need to have our finger on the pulse of the latest algorithms and frameworks coming up in the community.

So, if you’re a:
Data science enthusiast
Machine learning practitioner
Data science manager
Deep learning expert

or any mix of the above, this article is for you.

Pranav Dar loved putting together this month’s edition given the sheer scope of topics we have covered. Where computer vision techniques have hit a ceiling (relatively speaking), NLP continues to break through barricades. Sparse Transformer by OpenAI seems like a great NLP project to try out next.

What did you think of this month’s collection? Any data science libraries or discussions I missed out on? Hit me up in the comments section below and let’s discuss!

more to read : https://bit.ly/2Jb2JoB

#machinelearning #datascience #deeplearning

✴️ @AI_Python_EN

Implementing a user friendly interface without the need to dig into the code for fastai

https://github.com/asvcode/Vision_UI

✴️ @AI_Python_EN

Even when involved in the design of the research, statisticians normally must spend time checking, cleaning, and setting up data, as well as on exploratory data analysis.

Often this can amount to a considerable amount of time. For projects that are repeated, much of this can be automated and should be, when feasible.

The first time, though, trying to cut corners at this stage can be a huge mistake.

As a general rule, we should never delete, recode, or transform a variable unless we know what it is and what it means. When we have missing data, we should try to find out why it is missing. Blind imputation is very risky.

It goes without saying that we shouldn't analyze it either until we know what it is and what it means.

A variable might look like a garbage field, but might actually be telling us that we have the wrong data or that something is seriously amiss with it. If we mechanically delete it, we will not know this.

All this janitorial work pays off in other ways too, by helping us get to know the data, for example.

✴️ @AI_Python_EN

"Fair is Better than Sensational:Man is to Doctor as Woman is to Doctor"
Do word embeddings really say that man is to doctor as woman is to nurse? Apparently not!
Nissim et al.: https://arxiv.org/abs/1905.09866
#ArtificialIntelligence #MachineLearning #NLProc #bias

✴️ @AI_Python_EN

Understanding Hinton’s Capsule Networks. Part I: Intuition.
Blog by Max Pechyonkin:
https://medium.com/ai³-theory-practice-business/understanding-hintons-capsule-networks-part-i-intuition-b4b559d1159b
#MachineLearning #DeepLearning #ArtificialIntelligence
✴️ @AI_Python_EN

AI-GAs: AI-generating algorithms, an alternate paradigm for producing general artificial intelligence
https://arxiv.org/abs/1905.10985
#ArtificialIntelligence #ArtificialGeneralIntelligence

✴️ @AI_Python_EN

A curated list of gradient boosting research papers with implementations.

https://github.com/benedekrozemberczki/awesome-gradient-boosting-papers

✴️ @AI_Python_EN

All You Need About Common #MachineLearning Algorithms

Here is the list of commonly used machine learning algorithms. The code is provided in both #R and #Python. These algorithms can be applied to almost any data problem:

✅Linear Regression
✅Logistic Regression
✅Decision Tree
✅SVM
✅Naive Bayes
✅kNN
✅K-Means
✅Random Forest
✅Dimensionality Reduction Algorithms
✅Gradient Boosting algorithms
✔️GBM
✔️XGBoost
✔️LightGBM
✔️CatBoost


#ai #datascienece

✴️ @AI_Python_EN

TensorFlow Graphics Library for Unsupervised Deep Learning of Computer Vision Model

github: https://github.com/tensorflow/graphics

#machinelearning #deeplearning #computervision

✴️ @AI_Python_EN

SimpleSelfAttention

The purpose of this repository is two-fold:
-demonstrate improvements brought by the use of a self-attention layer in an image -classification model.
introduce a new layer which I call SimpleSelfAttention


https://github.com/sdoria/SimpleSelfAttention

✴️ @AI_Python_EN

website, which will provide you all up-to-date and necessary information on #ArtificialIntelligence, #MachineLearning, Deep Learning and some brain activities. You will also find TED Talks, Lectures and academic writings on these issues.

https://www.newworldai.com/

✴️ @AI_Python_EN

How to read a scientific paper

#paper
✴️ @AI_Python_EN

EfficientNet: Improving Accuracy and Efficiency through AutoML and Model Scaling

http://ai.googleblog.com/2019/05/efficientnet-improving-accuracy-and.html

✴️ @AI_Python_EN

Set of animated Artificial Intelligence cheatsheets covering Stanford's CS 221 class:

Reflex-based: http://stanford.io/2EqNPHy
States-based: http://stanford.io/2wh4F7u
Variables-based: http://stanford.io/2HAiAfh
Logic-based: http://stanford.io/2M7taia

GitHub: https://github.com/afshinea/stanford-cs-221-artificial-intelligence

✴️ @AI_Python_EN

Working with mini-imagent for few-shot classification? You might be interested in the pre-trained features from the LEO authors: https://github.com/deepmind/leo 🤖 Great to see these open sourced!

✴️ @AI_Python_EN

MNIST reborn, restored and expanded. Now with an extra 50,000 training samples. If you used the original MNIST test set more than a few times, chances are your models overfit the test set. Time to test them on those extra samples. https://arxiv.org/abs/1905.10498

✴️ @AI_Python_EN

The field of statistics has very long history, dating back to ancient times.

Much of marketing data science can be traced to the origins of actuarial science, demography, sociology and psychology, with early statisticians playing major roles in all of these fields.

Big is relative, and statisticians have been working with "big data" all along. "Machine learners" such as SVM and random forests originated in statistics, and neural nets were inspired as much by regression as by theories of the human brain.

Statisticians are involved in a diverse range of fields, including marketing, psychology, pharmacology, economics, meteorology, political science and ecology, and have helped developed research methods and analytics for nearly any kind of data.

The history and richness of #statistics is not always appreciated, though. For example, this morning I was asked "How's your #machinelearning?" :-)

✴️ @AI_Python_EN

#NLP Podcast by Allen Institute for AI


✴️ @AI_Python_EN

💡💡 K-means Clustering – In-depth Tutorial with Example 💡💡

Credits - Data Flair

Link - https://lnkd.in/eCQUriR

#machineleaning #supervisedlearning #unsupervisedlearning #datascience #data #ai # #technology #deeplearning #artificalintelligence

✴️ @AI_Python_EN

Sampling is a deceptively complex subject, and some academic statisticians have devoted the bulk of their careers to it.

It's not a subject that thrills everyone but is a very important one, and one which seems underappreciated in marketing research and #data science.

Here are some books on or related to sampling I've found helpful:

- Survey Sampling (Kish)
- Sampling Techniques (Cochran)
- Model Assisted Survey Sampling (Särndal et al.)
- Sampling: Design and Analysis (Lohr)
- Practical Tools for Designing and Weighting Survey Samples (Valliant et al.)
- Survey Weights: A Step-by-step Guide to Calculation (Valliant and Dever)
- Complex Surveys (Lumley)
- Hard-to-Survey Populations (Tourangeau et al.)
- Small Area Estimation (Rao and Molina)

The first three are regarded as classics (though still relevant.) Sharon Lohr's book is the friendliest introduction I know of on this subject. Standard marketing research textbooks also give simple overviews of sampling but do not get into depth.

There are also academic journals that feature articles on sampling, such as the Public Opinion Quarterly (AAPOR) and the Journal of Survey #Statistics and Methodology (AAPOR and ASA).

✴️ @AI_Python_EN

Zero-shot Knowledge Transfer via Adversarial Belief Matching
Interesting paper on training student networks using a teacher network, without having access to the original training set.
Nowadays most pre-trained models are released without access to the actual data. The original data set might be sensitive in nature or very large. The idea here is to train a second network to learn the decision boundary of the large network.

Code:
http://bit.ly/2X9ChQt

Paper:
http://bit.ly/2XauCRS

✴️ @AI_Python_EN