(Mohammed-Zarii)

intersted in #python #MachineLearning #deeplearning #datascience & #quantumcomputation

[Murat Durmus @CEO_AISOMA]

Data Science from the philosophical perspective 😉

#DataScience #MachineLearning #Statistics #AI #philosophy #FridayThoughts #100DaysOfCode #thoughtoftheday #100DaysOfMLCode #defstar5 #weekendvibes

[Kirk Borne @KirkDBorne]

This week's featured articles & resources for #DataScientists at @DataScienceCtrl → https://t.co/maWlXSuDZE
——————
#BigData #DataScience #DeepLearning #MachineLearning #AI #NeuralNetworks #Algorithms #Statistics #RPA #ReinforcementLearning #abdsc

[Vidit Nanda @viditnanda]

Introducing 🔥GeoTorch🔥, my student Mario L Casado's cool new library for optimization on interesting Riemannian manifolds. It handles Stiefel varieties, Grassmannians, and Lie groups! If you're thirsty for deep learning on SO(n), check it out :)

https://t.co/5Aawk0F8wP

[Kirk Borne @KirkDBorne]

List of #TimeSeries Analysis and #Forecasting Methods in One Picture: https://t.co/UkXFakQM3x
—————
#BigData #DataMining #DataScience #Statistics #IoT #IoTPL #IIoT #MachineLearning #PredictiveModeling #PredictiveAnalytics #Algorithms #abdsc

[Kirk Borne @KirkDBorne]

Explore the #Algorithms of #DataScience & #MachineLearning in their business applications context in this surprisingly informative book:

“#DataMining Techniques for Marketing, Sales and Customer Relationship Management” (3rd Ed.): https://t.co/yw7DavgJ2g

#CRM #CX #BigData #AI

[(Mohammed-Zarii) @Alzarii]

regression is basically to find best curve to fit the scattered points in the data , which can be used in continuous numerical labels, in the other side classifiers are used to categorize your data into groups of two or more the labels don't have to be numerical
#MachineLearning

[(Mohammed-Zarii) @Alzarii]

supervised #MachineLearning in life cycle
(1) split your data (training / test)
(2) train the training data to create a model
(3) test the model using the test data
(4) check its accuracy (if bad modify your model or check your data)
(5) use it to predict with different data

[Kirk Borne @KirkDBorne]

Backpropagation in #MachineLearning and #Finance, Explained in 15 mins: https://t.co/fNKH8dzZfM
——————
#BigData #DataScience #AI #DeepLearning #NeuralNetworks #Algorithms #Mathematics #abdsc
———
Source for graphic: https://t.co/kriLOxy02U

[(Mohammed-Zarii) @Alzarii]

a scalar [ ] = rank 0 tensor (requires no directions)
a vector [n]= rank 1 tensor (requires one directions)
a matrix [n,m]= rank 2 tensor (requires two directions)
in the RHS a tensor of [4,4,2] it is like having two matrices of size 4 by 4 in a single container
#TensorFlow

[Robert Lange @RobertTLange]

Beautiful overview of Bayesian Methods in ML by @shakir_za at #MLSS2020. Left me pondering about many things beyond Bayesian Inference. Thank you Shakir🙏

Quote of the day: “The cyclist, not the cycle, steers.“🚴‍♀️

🎤 P-I: https://t.co/yWR4BSJlw5
🎤 P-II: https://t.co/ipwwYCgGC4

[(Mohammed-Zarii) @Alzarii]

Sklearn made it very easy to select the best classifier #MachineLearning

[David Duvenaud @DavidDuvenaud]

We just open-sourced differentiable SDE solvers in PyTorch:
https://t.co/v1f08mjgCq
Now you can put stochastic differential equations in your deep learning models, and neural nets in your SDEs! Credit to @lxuechen.

[Mario @PawlowskiMario]

Mobile #3Dprinter can build an entire house in under a day🤯

@mashable V/@PawlowskiMario #3DPrinting #AI #Construction #Industry40 #4IR #tech #ML #EmergingTech #innovation

@RagusoSergio @HeinzVHoenen @MargaretSiegien @Paula_Piccard @jblefevre60 @ShiCooks

[Papers with Code @paperswithcode]

🎉 Introducing... Methods! We are now tracking 730+ building blocks of machine learning: optimizers, activations, attention layers, convolutions and much more! Compare usage over time and explore papers from a new perspective. Browse the catalogue here: https://t.co/XGFUzV3ELU

[(Mohammed-Zarii) @Alzarii]

Not too bad for regression

[Philipp Singer @ph_singer]

Pytorch offers free! version of their new book "Deep Learning with PyTorch" https://t.co/wGySa41UOl

[(Mohammed-Zarii) @Alzarii]

https://t.co/oVl1hCTtU3

[(Mohammed-Zarii) @Alzarii]

https://t.co/rO3NWNasbn

[(Mohammed-Zarii) @Alzarii]

#MachineLearning in life cycle
(1) get the data ready
(2) split your data
(3) train one part
(4) test the another
(5) observe the error
(6) try to improve the model (don't over fit)
(7) use it to predict