Can we learn to detect objects without any supervision? Yes, if we assume that an object is a part of an image that can be redrawn while keeping the image realistic. With Mickael Chen and Thierry Artieres - https://arxiv.org/abs/1905.13539

✴️ @AI_Python_EN

Deep reinforcement learning algorithms are impressive, but only when they work. In reality, they are largely unreliable and can yield very different results. larocheromain proposes two ways to achieve reliability in RL: https://aka.ms/AA5ann9 #ICML2019

The Enigma of Neural Text Degeneration as the First Defense Against Neural Fake News
If you want a sneek-peek in Yejin Choinka,and co-workers work on GROVER (a 1.5 billion param GPT-2-like model), check this live tweet 👇 Interesting hints, results, and analysis!
Paper: https://arxiv.org/abs/1905.12616
Demo: http://rowanzellers.com/grover/

✴️ @AI_Python_EN

Keras notebooks


Material used for Deep Learning related workshops for Machine Learning Tokyo (MLT)

ConvNets: colab notebook with functions for constructing #keras models. Models:

AlexNet
VGG
Inception
MobileNet
ShuffleNet
ResNet
DenseNet
Xception
Unet
SqueezeNet
YOLO
RefineNet

https://github.com/Machine-Learning-Tokyo/DL-workshop-series

✴️ @AI_Python_EN

Looking to enhance your NLP skills but unfamiliar with mathematics and linguistic structures ?!

Statistical Natural Language Processing by Manning Schuetze covers :
1) Mathematical foundations

2) Linguistic essentials

3) Corpus-Based work

4) Most useful clustering models in supervised and unsupervised methods

5) Lexical Acquisition

and so much more !




📕 @AI_Python_EN

We're now available via #linkedin :)

link :
https://www.linkedin.com/groups/13723396/


✴️ @AI_Python_EN

We have an opening for a post-doc position in my lab (http://fias.uni-frankfurt.de/en/neuro/triesch) at the Frankfurt Institute for Advanced Studies (FIAS) to study Open-Ended Deep Reinforcement Learning in simulated robots. We study systems that effectively learn to control their bodies and their environment by defining their own learning goals, practicing the skills for achieving these goals and setting themselves progressively harder goals. The work will be performed in the context of the European GOAL-Robots project (http://www.goal-robots.eu). For a quick overview of the project, check out this video:https://youtu.be/sordZmyp8u8. The focus of this post-doc position will be on simulated humanoids learning visually guided object interaction.

We are seeking an outstanding and highly motivated post-doc for this project. Applicants should have obtained a PhD in Machine Learning, Robotics, or a closely related field. The ideal candidate will have excellent programming and analytic skills and a broad knowledge of machine learning, robotics, and vision. An interest in cognitive development in human infants is a plus.

The Frankfurt Institute for Advanced Studies (https://fias.institute/en/) is a research institution dedicated to fundamental theoretical research in various areas of science. The city of Frankfurt is the hub of one of the most vibrant metropolitan areas in Europe. It boasts a rich culture and arts community and repeatedly earns high rankings in worldwide surveys of quality of living.

Applications should be sent as a single pdf file to triesch@fias.uni-frankfurt.de. Please include a brief statement of research interests, CV, and contact information for at least two references. The position can be filled immediately and applications will be reviewed on a continuing basis. The initial appointment will be for one year.

✴️ @AI_Python_EN

Computational Narrative Intelligence and the Quest for the Great Automatic Grammatizator
Slides by Mark Riedl: https://www.dropbox.com/s/2o8enj7amaxxx1y/naacl-nu-ws.pdf?dl=0
#ArtificialIntelligence #MachineLearning #NaturalLanguageProcessing

✴️ @AI_Python_EN

Practical Deep Learning with Bayesian Principles
Osawa et al.: https://arxiv.org/pdf/1906.02506.pdf
#Bayesian #DeepLearning #PyTorch #VariationalInference

✴️ @AI_Python_EN

All 1,294 papers at #CVPR2019
Index: http://openaccess.thecvf.com/content_CVPR_2019/html/
#ArtificialIntelligence #DeepLearning #MachineLearning

✴️ @AI_Python_EN

Best of arXiv.org for AI, #MachineLearning, and Deep Learning – April 2019 by insidebigdata

https://insidebigdata.com/2019/05/22/best-of-arxiv-org-for-ai-machine-learning-and-deep-learning-april-2019/

✴️ @AI_Python_EN

Yann LeCun et al. publishing evolutionary algorithm tools. Welcoming the era of deep neuroevolution indeed! (https://eng.uber.com/deep-neuroevolution) Great to see the traditional ML community adopt these tools in the cases when they are useful.

✴️ @AI_Python_EN

Hot Papers from Google Brain, DeepMind and Facebook AI

https://www.google.com/amp/s/syncedreview.com/2019/06/02/hot-papers-from-google-brain-deepmind-and-facebook-ai/amp/

✴️ @AI_Python_EN

Material used for Deep Learning related workshops for Machine Learning Tokyo
Implementation and Cheat Sheet: https://github.com/Machine-Learning-Tokyo/DL-workshop-series
#artificialintelligence #deeplearning #machinelearning

✴️ @AI_Python_EN

This is probably the best #PyTorch Deep Learning course I have encountered.
https://fleuret.org/dlc/

✴️ @AI_Python_EN

Below are 44 frequently asked question (and answer) on Deep Learning key principles

✴️ @AI_Python_EN

Here is a full list of Iranian Female Researchers presenting at ICML poster sessions and workshops! Don't forget to support them!

https://lnkd.in/gbq2hmu

✴️ @AI_Python_EN

In my view, data are guilty until proven innocent. By that I mean we cannot assume they are error free and honest in what they seem to be telling us. Justice in statistics can be harsh. :-)

Statisticians working with consumer survey data for the first time are often alarmed when they dig into the data. They can be especially critical of the questionnaire, which may have been designed by a person or persons with no formal background in survey research.

Many questions may make little sense to most people, or have different meanings to different people. Answer categories may overlap or be ambiguous in other ways.

People vary in response styles too and, furthermore, their attention may wander during sections of the questionnaire of little interest to them.

In the worst case, important marketing decisions may be made on the basis of how respondents interacted with the survey instrument.

Fortunately, besides professional questionnaire design, there are statistical means psychometricians have developed which can help reduce the noise in survey data.

This is a big topic and I can't do justice to it in a short LI post, other than to say statisticians familiar with survey research now have a multitude of tools to help them clean survey data and avoid being "conned." .Kevin Gray

✴️ @AI_Python_EN

Top Java, Deep Learning, DevOps And AWS Interview Questions You Must Know (2019)

It is the updated version for anyone who is going to have an interview soon or even challenge yourself to test your understandings of #Deeplearning.

✅100+ #Java Interview Questions You Must Prepare In 2019:
https://lnkd.in/gr2djip
✅Most Frequently Asked #AI Interview Questions
https://lnkd.in/g6Q89dn
✅Top #AWS Architect Interview Questions In 2019
https://lnkd.in/gecpceu
✅Top #DevOps Interview Questions You Must Prepare In 2019
https://lnkd.in/gTCFCyt

✴️ @AI_Python_EN

*******The Algorithms*******

Open Source Resource for Newbies to Learn Algorithms and Implement them in any Programming Language.

Github Link - https://lnkd.in/edw2vHj

#pythonprogramming #python #java #scala #c #cplusplus #csharp

✴️ @AI_Python_EN

💡💡 Commonly used Machine Learning 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

Credit: Analytics Vidhya,Sunil Ray

Thanks for the share Steve Nouri.

#datascience #deeplearning #ai #artificialintelligence #machinelearning #data #r #python

✴️ @AI_Python_EN