Useful #Linux cheat sheet for #datascientists

✴️ @AI_Python_EN

A great GitHub repository with tutorials on getting started with #PyTorch and TorchText for #sentimentanalysis in #Jupyter Notebooks. What a great resource!

https://github.com/bentrevett/pytorch-sentiment-analysis

✴️ @AI_Python_EN

#Datascience needs to move beyond #research to actually make a real impact in the #AI economy.

Agree?

#DeepLearning #artificialintelligence #machinelearning

✴️ @AI_Python_EN

Here is a list of handy tools to keep in your #DataScience toolbox:

- - -
➤ Data Science Platform (All-in-one Packages & IDE)
Anaconda - https://lnkd.in/gWHY_ij

➤ Programming Languages (Python, R, and SQL)
Python Zero-to-Hero
https://lnkd.in/gEyZd5W
SQL for Data Science
https://lnkd.in/gjvgdhZ
(https://lnkd.in/fZxEF-g)

➤ Data Science Libraries
Top 15 Python Libraries (SciKit-Learn, TensorFlow, NLTK, matplotlib, etc..)
https://lnkd.in/gw_f3Ga

➤ Distributed Systems (Spark, Hadoop, Kafka)
Spark - https://lnkd.in/gC92A64
Hadoop - https://lnkd.in/gKuxgwx
Kafka - https://lnkd.in/gBB9Ja7

➤ Version Control (Git)
https://lnkd.in/g5sJj2H

➤ Reproducibility and Virtual Machines (Docker)
https://lnkd.in/gzYjuuA

➤ Cloud Services (AWS, Google Cloud, Microsoft Azure)
https://lnkd.in/gBJeQuY

➤ Serverless Architecture (Firebase)
https://lnkd.in/gbB6eeM

Data Warehouse and Data Lake
https://lnkd.in/gepNRMw


- - -
This list contains a high-level overview of the many tools out there that can be used for Data Science.

It's always great to refer back to your tools and keep things in check.

Hope this helps 🙂

✴️ @AI_Python_EN

The Full Stack #DeepLearning Bootcamp was a lot of fun in person, but of course not everyone can make it in person. Very excited to start releasing the materials today, here:

https://lnkd.in/giizppb

Happy learning from home!

✴️ @AI_Python_EN

Haha so funny! A typical day in the life of a machine learner 😂 #deeplearning #machinelearning #fun

✴️ @AI_Python_EN

Weakly Supervised Gaussian Networks for Action Detection
Researchers: Basura Fernando, Cheston Tan Yin Chet, Hakan Bilen
Paper: http://ow.ly/NC0S50qAP7S

#artificialinteligence #machineleaning #bigdata #machinelearning #deeplearning

✴️ @AI_Python_EN

Good start on mastering a new skill from scratch.

some of covered topics are :
1) Careers (complete learning paths to become a master)
2) Topics (comprehensive guides about a specific topic)
3) Tools
4) Reasearch

https://github.com/clone95/Virgilio

#machinelearning #AI #getting_started
@AI_Python_EN

Starting weights can matter a lot for training a neural net. Read this deeplearning.ai tutorial on initializing your neural network:
http://bit.ly/2XmzHGu

✴️ @AI_Python_EN

Wow nice there's a new convolution operation for CNNs called "Octave Convolution (OctConv)" which can be used as a direct replacement of plain vanilla convolutions without any adjustments in the network architecture. The idea of OctConv is pretty cool. In images, information is conveyed at different frequencies i.e. high frequencies show fine details whereas low-frequencies show global structures.

The idea then is to factorize the feature maps into a high-frequency/low-frequency feature maps and then reduce the spatial resolutions of the low-frequency maps by an octave. This not only leads to lower memory/computation cost but also to better evaluation results such as accuracy in an image classification task. Can't wait to see this in Keras/TensorFlow! #deeplearning #machinelearning

Paper: https://lnkd.in/dckWSDq

✴️ @AI_Python_EN

Ian Goodfellow: Generative Adversarial Networks (GANs)
This conversation with Ian led me to rethink the way I see several basic ideas in deep learning, including generative models, adversarial learning, and reasoning. I definitely enjoyed it and hope you do as well.

Ian Goodfellow: Generative Adversarial Networks (GANs)

✴️ @AI_Python_EN

17 equations that changed the world
✴️ @AI_Python_EN

#DeepLearning is fun when you have loads of GPUs!

Here's a 256GB , 8 GPU cluster we will soon be testing as well.

#gpu #nvidia #research
#machinelearning
✴️ @AI_Python_EN

✴️ @AI_Python_EN

Stanford ML Group just released knee injury dataset they're calling MRNET.

Paper: https://lnkd.in/dwik_zz

Dataset: https://lnkd.in/dwS96AD
#ml #knee #injury #stanford #dataset #deeplearning

https://lnkd.in/dDpD38u

✴️ @AI_Python_EN

Neural Painters: A learned differentiable constraint for generating brushstroke paintings

Nice paper combining ideas from world models and style transfer

paper: https://lnkd.in/gpWm3y9

github: https://lnkd.in/gVuExnm


✴️ @AI_Python_EN

Great explanation of permutation test.
Should alpacas be shampooed? ;-)

https://lnkd.in/eXqA7ze

✴️ @AI_Python_EN

What make a company don't want spend on #AI development?

A. Don't have budget
B. Don't understand what is AI
C. Just stingy in general
D. Talent shortage
E. No satisfying consultant/vendor in their area
F. Other, ...

I'm courious about your experience, please choose, if you have multiple reason please start from most relevant one.

✴️ @AI_Python_EN

Datasheets for Datasets

http://arxiv.org/abs/1803.09010

#Databases #ArtificialIntelligence #AIEthics #Ethics #MachineLearning

✴️ @AI_Python_EN

CS294-158 Deep Unsupervised Learning Spring 2019

About: This course will cover two areas of deep learning in which labeled data is not required: Deep Generative Models and Self-supervised Learning.

Instructors: Pieter Abbeel, Peter Chen, Jonathan Ho, Aravind Srinivas

CS294-158: https://lnkd.in/eq6ZKAn

#DeepLearning #GenerativeModels #UnsupervisedLearning

✴️ @AI_Python_EN

Some random thoughts on p-values...

Inferential statistics comes into play when we wish to generalize a result from a sample to the population from which the sample was drawn.

The type of sampling procedure used must be taken into account. This is important since most statistical programs assume simple random sampling.

The quality of the sample and the definition of the population must also be considered. A textbook-quality sample from the wrong population, for example, could seriously mislead us.

Coverage problems and non-response in the case of surveys can be serious problems.

Measurement error and missing data can wreak havoc on the fanciest of analytics.

Distributional assumptions should not be ignored.

The "So What?" test, IMO, is most important. A very large and highly statistically significant correlation may have little significance to decision-makers. Conversely, a tiny correlation might be big news.

After a 100 years, if so many scientists and researchers still can't get their heads around p-values, what are the chances that Bayesian statistics will fare any better?

For much deeper thoughts on this important topic, see "Statistical Inference in the 21st Century: A World Beyond p < 0.05", linked below.



"Total Survey Error: Past, Present, and Future" may also be of interest -
https://academic.oup.com/poq/article/74/5/849/1817502


Inferential statistics are often used inappropriately, IMO. One example would be performing a t-test to assess whether a regression coefficient is really zero in the population...when the regression was performed on the population data. Similarly, significance testing is frequently used in model diagnostics when it might be more sensible to investigate how potential violation of an assumption might be affecting the model.



"Statistical Inference in the 21st Century: A World Beyond p < 0.05" -
https://www.tandfonline.com/toc/utas20/current

✴️ @AI_Python_EN