Topics Extraction and Classification of Online Chats

This article provides covers how to automatically identify the topics within a corpus of textual data by using unsupervised topic modelling, and then apply a supervised classification algorithm to assign topic labels to each textual document by using the result of the previous step as target labels.

Link to the article

🔭 @DeepGravity

#Python programming language creator retires, saying: 'It's been an amazing ride'

Guido van #Rossum, the creator of the hugely popular Python programming language, is leaving cloud file storage firm Dropbox and heading into retirement.

That ends his six and half years with the company, which hired in him in 2013 because so much of its functionality was built on Python. And, after last year stepping down from his leadership role over Python decision making, that means the Python creator is officially retiring.

His recruitment at Dropbox made sense for the tech company. Dropbox has about four million lines of Python code and it's the most heavily used language for its back-end services and desktop app.

Read the article here

🔭 @DeepGravity

#MIT Technology Review:
A #NeuralNet solves the three-body problem 100 million times faster

#MachineLearning provides an entirely new way to tackle one of the classic problems of applied #mathematics.

Link to the article

Link to the paper

🔭 @DeepGravity

Ali Ghodsi (a CS prof. at University of Waterloo) is absolutely a great #AI teacher. Download some of his lectures on #DeepLearning here (part1) (part2).
If you are interested you might find all his lectures on his YouTube channel.

⚠️ Bofore downloading: the zipfiles include:

02 - Feedforward neural network
03 - Overfitting
04 - Introduction to Keras
05 - Regularization
06 - Batch Normalization
07 - Convolutional neural network and a simple implementation in Keras
08 - Recurrent neural network
09 - LSTM, GRU
10 - Variational Autoencoder
11 - Generative Adversarial Network

🔭 @DeepGravity

Ali Ghodsi (a CS prof. at University of Waterloo) is absolutely a great #AI teacher. Download some of his lectures on #DeepLearning here (part1) (part2).
If you are interested you might find all his lectures on his YouTube channel.

⚠️ Bofore downloading: the zipfiles include:

02 - Feedforward neural network
03 - Overfitting
04 - Introduction to Keras
05 - Regularization
06 - Batch Normalization
07 - Convolutional neural network and a simple implementation in Keras
08 - Recurrent neural network
09 - LSTM, GRU
10 - Variational Autoencoder
11 - Generative Adversarial Network

🔭 @DeepGravity

20 useful #Python tips and tricks you should know

Link to the paper

🔭 @DeepGravity

#Tensorflow 2.0 coding workshop notebooks

At our meetup Data Science for Internet of Things, Dan Howarth conducted a workshop on tensorflow 2.0
we plan to convert it into another book on data science central. for a set of all previous free books see free datascience books. The notebooks are

tensorflow 2.0: Notebook 1: 'Hello World' Deep Learning with Tensor...

tensorflow 2.0: Notebook 2: Computer Vision with CNNs

tensorflow 2.0: Notebook 3: Transfer Learning

You can see the tensorflow 2.0 roadmap and overall features of tensorflow 2.0. Comments welcome. We hope you like them.

Link to the paper

🔭 @DeepGravity

#Netflix Open Sources Polynote to Make #DataScience Notebooks Better
The new notebook environment provides substantial improvements to streamline experimentation in #MachineLearning workflows.

Link to the paper

🔭 @DeepGravity

Don’t Ever Ignore #ReinforcementLearning Again

#Supervised or #unsupervised learning is not everything. Everyone knows that. Get started with #OpenAI #Gym.

Link to the article

🔭 @DeepGravity

Top 10 roles in AI and data science
0 Data Engineer
1 Decision-Maker
2 Analyst
3 Expert Analyst
4 Statistician
5 Applied Machine Learning Engineer
6 Data Scientist
7 Analytics Manager / Data Science Leader
8 Qualitative Expert / Social Scientist
9 Researcher
10+ Additional personnel

Read the article here

🔭 @DeepGravity

The Fundamentals of #Matplotlib

Having a good grasp of these basics will greatly ease your foray into the expansive world of data visualization.

Link to the article

🔭 @DeepGravity

Postdoctoral / Research Staff Member Position at IBM Research (Zurich) on Unifying Learning and Reasoning

Post-doc position in machine listening/Inria Nancy -- Grand Est, France

PhD Position in Deep Learning for Robotics at Istanbul Technical University (Turkey), in collaboration with Halmstad University (Sweden)

Positions in Machine Learning and Game Playing

Robot/Reinforcement/Deep Learning Research Associate Positions in Cyprus

#Job

🔭 @DeepGravity

Seems tolch.av used GANtools to generated this interesting GIF.

#GANs
#GenerativeAI

🔭 @DeepGravity

A new tool uses #AI to spot text written by AI

AI algorithms can generate #text convincing enough to fool the average human—potentially providing a way to mass-produce fake news, bogus reviews, and phony social accounts. Thankfully, AI can now be used to identify fake text, too.

Link to the article

🔭 @DeepGravity

Keras Tuner is a new #Keras wrapper that uses #sklearn grid search for tunning the hyperparameters of #deepLearning models

Link to Tuner documentation

Link to a related article

🔭 @DeepGravity

How to Develop a #Pix2Pix #GAN for Image-to-Image Translation

Link to the paper

🔭 @DeepGravity

Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model

Constructing agents with planning capabilities has long been one of the main challenges in the pursuit of artificial intelligence. Tree-based planning methods have enjoyed huge success in challenging domains, such as chess and Go, where a perfect simulator is available. However, in real-world problems the dynamics governing the environment are often complex and unknown. In this work we present the MuZero algorithm which, by combining a tree-based search with a learned model, achieves superhuman performance in a range of challenging and visually complex domains, without any knowledge of their underlying dynamics. MuZero learns a model that, when applied iteratively, predicts the quantities most directly relevant to planning: the reward, the action-selection policy, and the value function. When evaluated on 57 different Atari games - the canonical video game environment for testing AI techniques, in which model-based planning approaches have historically struggled - our new algorithm achieved a new state of the art. When evaluated on Go, chess and shogi, without any knowledge of the game rules, MuZero matched the superhuman performance of the AlphaZero algorithm that was supplied with the game rules.

Link to the main paper

Link to a related article

#MuZero
#DeepMind
#ReinforcementLearning

🔭 @DeepGravity

OpenAI releases Safety Gym for reinforcement learning

To study constrained #RL for safe exploration, we developed a new set of environments and tools called #SafetyGym. By comparison to existing environments for constrained RL, Safety #Gym environments are richer and feature a wider range of difficulty and complexity.

Link to the Safety Gym

Link to a related article

#OpenAI
#ReinforcementLearning

🔭 @DeepGravity

A lot of #DataScience Cheatsheets such as #DeepLearning #Python #Docker

Link to the Github repo

🔭 @DeepGravity

#DeepLearning with #PyTorch

Download a free copy of the book and learn how to get started with #AI / #ML development using PyTorch

#Python

🔭 @DeepGravity

#MachineLearning for Scent: Learning Generalizable Perceptual Representations of Small Molecules

Predicting the relationship between a molecule’s structure and its odor remains a difficult, decades-old task. This problem, termed quantitative structure-odor relationship (QSOR) modeling, is an important challenge in chemistry, impacting human nutrition, manufacture of synthetic fragrance, the environment, and sensory neuroscience. We propose the use of graph neural networks for QSOR, and show they significantly outperform prior methods on a novel data set labeled by olfactory experts. Additional analysis shows that the learned embeddings from graph neural networks capture a meaningful odor space representation of the underlying relationship between structure and odor, as demonstrated by a strong performance on two challenging transfer learning tasks. Machine learning has already had a large impact on the senses of sight and sound. Based on these early results with graph neural networks for molecular properties, we hope machine learning can eventually do for olfaction what it has already done for vision and hearing.

Link to the paper by #Google Research and ...

🔭 @DeepGravity