We are Available in Persian

Python and Linux :

https://t.me/PythonLinuxExperts

DeepLearning and Artificial Intelligence:

https://t.me/DeepLearningAIExperts

Natural Language Processing and Data Mining:

https://t.me/NLPExperts

--Activation Function in CNN--
-Image Analysis-

#imageanalysis #machinelearning #clustering #datascientists #kmeans #deeplearning #neuralnetwork #underfitting

Urban legends about regression abound...Regression is much more than OLS linear or binary logistic regression.

Normally distributed data are not a requirement. Regression is not limited to modeling linear relationships. Data correlated across time or cross-sectionally can be accommodated, as can data from mixed distributions.

Some extensions of regression are able to simultaneously model multiple dependent variables of any data type - continuous, interval, ordinal, nominal and count. Some can include latent (unobserved) variables on either side of the equation.

For those with a basic background in regression, this book by two leading authorities, is an excellent next step.
https://www.crcpress.com/Generalized-Linear-Models-and-Extensions-Fourth-Edition/Hardin-Hilbe/p/book/9781597182256

✴️ @AI_Python_EN

Machine Learning VS Deep Learning

#machinelearning #artificialintelligence #datascience #ml #ai #deeplearning #technology #python

✴️ @AI_Python_EN

This is a classic JMR paper on segmentation by Yoram ("Jerry") Wind, one of the academic titans of marketing research in the latter part of the 20th century.

Many things have changed since 1978 when the article was published, but many have not.

This entire issue was devoted to segmentation and history buffs with JMR access can have their fill.

✴️ @AI_Python_EN

Tackling Climate Change with Machine Learning

Rolnick et al.: https://lnkd.in/eqqV9wr

#artificialintelligence #climatechange #climatecrisis
#machinelearning

✴️ @AI_Python_EN

It is a good feeling when a popular Python package adds a new feature based on your article :-)

#Yellowbrick is a great little #ML #visualization library in the Python universe, which extends the Scikit-Learn API to allow human steering of the model selection process, and adds statistical plotting capability for common diagnostics tests on ML.

Based on my article "How do you check the quality of your regression model in Python? they are adding a new feature to the library - Cook's distance stemplot (outlier detection) for regression models.

#python #datascience #machinelearning #data #model
https://www.scikit-yb.org/en/latest/

✴️ @AI_Python_EN

Sybil-Resilient Reality-Aware Social Choice. - A new Paper by Gal Shahaf et al. in #MultiAgent Systems

Paper: https://bit.ly/2TgeqvG

#artificialintelligence #machinelearning

✴️ @AI_Python_EN

Don't mess with Robots! 😂😂

#robots #robotics #ai #artificialintelligence #machinelearning #deeplearning #datascience #dataanalytics #bigdata #computervision #automation #technology #innovation #emergingtechnologies

Bosstown Robotics

✴️ @AI_Python_EN

I am implementing a training loop that can be used with Auxiliary Classifier. So what is an Auxiliary Classifier?

Auxiliary Classifier are the ones in which we take the outputs of layers of some previous layers along with the final outputs and compare it with the targets and calculate a loss based on both the outputs from the final layer as well as the previous layer.

How does this help?
I think before even me saying how this is going to be helpful, I think this intuitively gives an idea of how is this going to aid the training process, I got so freaking excited when I came to know about this.

So, How does this help?
- Solves the gradient Vanishing problem
- Low-level features get more and more accurate and thus making the model more and more accurate.
- This also acts as regularization, it kind of can be thought as putting some constraints on the model which help in regularization.

I am not sure which paper first introduced Auxiliary Approaches, but I am trying to train an FCN using this, let's see how this aids the process :)
Maybe the Inception paper.

#machinelearning #deeplearning #datascience #python #artificialintelligence #selfdriving #nlp #computervision

✴️ @AI_Python_EN

Using Neural Networks to perform makeup.
#neuralnetwork #ComputerVision
#Artificialntelligence

https://medium.com/mathematical-beauty/deep-learning-for-cosmetics-2d1b427bbfa2

✴️ @AI_Python_EN

Frankly, the process of machine learning is quite basic. But it pretty much runs the world.
https://www.technologyreview.com/s/612437/what-is-machine-learning-we-drew-you-another-flowchart/

✴️ @AI_Python_EN

Releasing STEAL, a new semantic boundary detector that significantly outperforms past work. Use STEAL to refine segmentation datasets, and train better segmentation models!
paper:https://arxiv.org/abs/1904.07934
code:https://github.com/nv-tlabs/STEAL
#computervision
✴️ @AI_Python_EN

✴️ @AI_Python_EN

Adobe Research and UC Berkeley: Detecting Facial Manipulations in Adobe Photoshop
https://theblog.adobe.com/adobe-research-and-uc-berkeley-detecting-facial-manipulations-in-adobe-photoshop/

✴️ @AI_Python_EN

Capturing Context in Emotion AI: Innovations in Multimodal Video Sentiment Analysis
#ComputerVision #MachineLearning #ArtificialIntelligence

http://bit.ly/2ZdU6yc

✴️ @AI_Python_EN

Contrastive Multiview Coding Paper+Code: https://github.com/HobbitLong/CMC/ Different views of the world capture different info, but important factors are shared. Learning to capture the shared info .
Extends / simplifies "Contrastive Predictive Coding" https://arxiv.org/abs/1807.03748 Main findings: 1. More views —> better reps 2. Contrastive learning outperforms predictive 3. On Imagenet, unsupervised Resnet-101 outperforms supervised Alexnet.

✴️ @AI_Python_EN

Interested in Continual (Lifelong) Learning? Come to the Workshop on Multi-Task and Lifelong Reinforcement Learning tomorrow (Saturday) ICML for posters and oral on how to rehearse on on older tasks efficiently!

✴️ @AI_Python_EN

Erin LeDell: Happy to share our #ICML2019 #AutoML Workshop paper, "An Open Source AutoML Benchmark". We present a new #opensource AutoML benchmarking system and include results on: H2O AutoML, auto-sklearn, TPOT, Auto-WEKA
📰 Paper: https://www.automl.org/wp-content/uploads/2019/06/automlws2019_Paper45.pdf
👩‍💻 Code: https://github.com/openml/automlbenchmark/

✴️ @AI_Python_EN