Auto-Keras

Auto-Keras is an open source software library for automated machine learning (AutoML).

GitHub: https://lnkd.in/eJAKXy5

#keras #deeplearning #machinelearning


✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_Arxiv

Deep Learning and Robotics

Slides by Pieter Abbeel: https://lnkd.in/eChDuNZ

#deeplearning #reinforcementlearning #robotics

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_Arxiv

Neural Reading Comprehension and Beyond

By Danqi Chen: https://lnkd.in/eY_PreF

#artificialintelligence #deeplearning #machinelearning #research #thesis

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_Arxiv

Looking for papers with code? If so, this GitHub repository, a clearinghouse for research papers and their corresponding implementation code, is definitely worth checking out.Join Us

#artificialintelligence #deeplearning #machinelearning #research #paper

https://www.kdnuggets.com/2018/12/papers-with-code-fantastic-github-resource-machine-learning.html

✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_Arxiv

Simple Alpha Zero

If you like our channel, i invite you to share it with your friends:

https://web.stanford.edu/~surag/posts/alphazero.html

✴️ @AI_Python_EN
🗣 @AI_Python_Arxiv

Interesting line of question by Y.Bengio about why quantum computing folks need to digitalize their systems:

https://www.youtube.com/watch?v=vfJuvNuSPKw

#quantumcomputing #deeplearning

✴️ @AI_Python_EN
🗣 @AI_Python_Arxiv

Topic Modeling with LSA, PSLA, LDA & lda2Vec – NanoNets

#deeplearning #machinelearning #artificialintelligence
https://bit.ly/2kxcq2Z

✴️ @AI_Python_EN
🗣 @AI_Python_Arxiv

Machine Learning models have a reputation for being difficult to explain. After all, they are, in some sense, sacrificing explainability for predictive accuracy.
In recent years, there's more interest in making ML models more explainable and, therefore, more trustworthy. The common example is that of a denied credit application: a customer would want to know why she has been rejected.
If you like our channel, i invite you to share it with your friends
LIME (locally interpretable model agnostic explanations) is method aimed at improving explainability. The following is a continuation of the LIME approach called Anchors. This presentation builds the intuition for it.

https://lnkd.in/ekJEqPz

#machinelearning #analytics #datascience #ml #statistics

✴️ @AI_Python_EN
🗣 @AI_Python_Arxiv

A Brief Survey of #Deep Reinforcement Learning

https://bit.ly/2rZSQAm

#مقاله
Deep Learning for Generic Object Detection: A Survey

https://bit.ly/2s3gw6M

✴️ @AI_Python_EN
🗣 @AI_Python_Arxiv

This #Algorithm Can Create 3D #Animations From A Single Still 2D Image.
A 2D subject in a single photo as input, and creates a 3D animated version of that subject. The animation can then walk out, run, sit, or jump in #3D.

#artificialintelligence #technology #research

https://lnkd.in/f8hxfcd #machinelearning
If you like our channel, i invite you to share it with your friends
✴️ @AI_Python_EN
🗣 @AI_Python_Arxiv

Pranoy made an #AI to automate colorizing black and white videos using #deeplearning with #pytorch.

Github: https://lnkd.in/fy7WeQ3
Pranoy provided a colab notebook to speed things up so feel free to check it out.

If you like our channel, i invite you to share it with your friends

✴️ @AI_Python_EN
🗣 @AI_Python_Arxiv

The 10 Biggest datasets of 2018

0) Open Images V4 from Google AI on April 30th Contains 15.4M bounding-boxes for 600 categories on 1.9M images.
Paper: https://lnkd.in/fm4xiUm

1) MURA from Stanford University ML Group on May 24 Radiographic image dataset
Paper: https://lnkd.in/fBy5szB

2) BDD100K from BAIR, Georgia Tech, Peking University, Uber AI
on May 30 Self-Driving Car Dataset.
Paper: https://lnkd.in/f-sYj9k

3) SQuAD 2.0 from Stanford
on June 11 QA Dataset.
Paper: https://lnkd.in/fYc6c5W

4) CoQA from Stanford on August 21 QA Dataset
Paper: https://lnkd.in/fKvuTvE

5) Spider 1.0 from Yale Univ on September 24 Cross-domain semantic parsing and text-to-SQL dataset.
Paper: https://lnkd.in/fWyR2x8

6) HototQA from Carnegie, Stanford, and Montreal on September 25 QA Dataset on Wiki
Paper: https://lnkd.in/fTtTgZt

7) Tencent ML Images from Tencent AI Lab on Oct 18 largest open-source multi-label image dataset
Paper: https://lnkd.in/ffV6VD5

8) Tencent AI Lab Embedding Corpus for Chinese words and phrases on Oct 19 Embeddings Dataset
Paper: https://lnkd.in/ffV6VD5

9) fastMRI from NYU and Facebook AI on November 26
Knee MRI Images Dataset
Paper: https://lnkd.in/fQuUDNk

Read: https://lnkd.in/fXU9Kr6

#dataset #datasets

✴️ @AI_Python_EN
🗣 @AI_Python_Arxiv

Predicting Aircraft Trajectories: A Deep Generative Convolutional Recurrent Neural Networks Approach.
http://arxiv.org/abs/1812.11670
#RNN #ML

✴️ @AI_Python_EN
🗣 @AI_Python_Arxiv

Hough transform simplified! Hough Transform and Line Detection with #Python
https://youtu.be/G019Av7XhGo

If you like our channel, i invite you to share it with your friends
✴️ @AI_Python_EN
🗣 @AI_Python_Arxiv

The Illustrated BERT, ELMo, and co. (How NLP Cracked Transfer Learning)

Blog by Jay Alammar: https://lnkd.in/ejqSjnZ

#NaturalLanguageProcessing #NLP #TransferLearning

If you like our channel, i invite you to share it with your friends

✴️ @AI_Python_EN
🗣 @AI_Python_Arxiv

Style-based GANs – Generating and Tuning Realistic Artificial Faces

#ML #GAN

https://bit.ly/2R5wqN2

If you like our channel, i invite you to share it with your friends

✴️ @AI_Python_EN
🗣 @AI_Python_Arxiv

DATASET DISTILLATION

Anonymous authors: https://lnkd.in/ekqYXTs

#artificialinteligence #deeplearning #machinelearning

If you like our channel, i invite you to share it with your friends

✴️ @AI_Python_EN
🗣 @AI_Python_Arxiv

My thoughts on R Vs. Python remains the same, learn both and master one. (If you master Python, it is well and good)

However, I came across hybrid scripting where data wrangling and manipulations are done using R, and machine learning functionalities are implemented using Python.

I feel this is the way to go and to learn both can enable a whole lot of possibilities than just knowing one language. So starting from today, I will be sharing more information on python as I do for R.

I have shared posts in the past discussing different python IDEs, and my favorite is Jupyter notebooks. Even though I love RStudio like environment, when it comes to python the functionality of a notebook attracts me a lot more than spyder or pycharm. I also got a suggestion of Visual studio code which I will be trying out soon.

I want to share some jupyter notebook hacks. It can increase your productivity drastically. Please have a look at it.

Link - https://lnkd.in/f7nkFxX

Hope this helps!

✴️ @AI_Python_EN
🗣 @AI_Python_Arxiv

Nice article on how TensorFlow 2.0 will look like, in particular with Keras more tightly integrated aka tf.keras. The most interesting new feature for us will be the model subclassing API. You can then build customizable models in a style of Chainer (Link: https://chainer.org/) which will offer us a much more flexible way of creating models. Other than that, you will get out-of-the-box support for multi-GPU training, exporting models and many more features. I guess in the future we won't need to install Keras separately anymore as TensorFlow is currently our main deep learning backend. #deeplearning #machinelearning

Article: https://lnkd.in/dWxcU-i

✴️ @AI_Python_EN
🗣 @AI_Python_Arxiv

Can AI Judge a Paper on Appearance Alone?

#AI
https://bit.ly/2CJSST8

✴️ @AI_Python_EN
🗣 @AI_Python_Arxiv