Collaborating Authors

Semi-supervised Anomaly Detection using Auto Encoders


In this article, I'll be discussing a paper [1] that proposes an AutoEncoder based approach for the task of semi-supervised anomaly detection. If you want to look at the GitHub repository link, results and conclusion directly, please scroll to the bottom of the article. Anomaly detection refers to the task of finding unusual instances that stand out from the normal data [1]. The non-conforming patterns can be referred to using different names depending on the application area/domain, such as anomalies, outliers, exceptions, defects, containments, etc. [2] In several applications, these outliers or anomalous samples are of greater interest compared to the normal ones. Specifically in the case of industrial surface inspection and infrastructure asset management, finding defects (anomalous regions) is of extreme importance.

ML.NET Model Builder November Updates


ML.NET is an open-source, cross-platform machine learning framework for .NET developers. It enables integrating machine learning into your .NET apps without requiring you to leave the .NET ecosystem or even have a background in ML or data science. ML.NET provides tooling (Model Builder UI in Visual Studio and the cross platform ML.NET CLI) that automatically trains custom machine learning models for you based on your scenario and data. This release of ML.NET Model Builder brings numerous bug fixes and enhancements as well as new features, including advanced data loading options and streaming training data from SQL. In this post, we'll cover the following items: Previously, Model Builder did not offer any data loading options, relying on AutoML to detect column purpose, header, and separator as well as decimal separator style.

Deep Reinforcement Learning for Ping Pong


In this post, you will implement an AI program(or agent if you want to be more fancy! If you are beginner to reinforcement learning this post is perfect for you as it tries to cover the essence of Reinforcement Learning. The code and a challenge link has been attached below So Follow along till the end..! For our case we use a game which is(you guessed it!) Ping Pong, as our environment, provided by OpenAI's library, as the environment for our AI. The AI gets control of one of the sliders only (green slider in our case).

Top 3 Emerging Technologies in Artificial Intelligence in the 2020s


Artificial Intelligence or popularly known as AI, has been the main driver of bringing disruption to today's tech world. While its applications like machine learning, neural network, deep learning have already earned huge recognition with their wide-ranging applications and use cases, AI is still in a nascent stage. This means, new developments are simultaneously taking place in this discipline, which can soon transform the AI industry and lead to new possibilities. So, some of the AI technologies today may become obsolete in the next ten years, and others may pave the way to even better versions of themselves. Let us have a look at some of the promising AI technologies of tomorrow.

Artificial intelligence solves 50-year-old science problem


For about 50 years, researchers have strived to predict how proteins achieve their three-dimensional structure, and it's not an easy problem to solve. Google's Deepmind claims to have created an artificially intelligent program called "AlphaFold" that is able to solve those problems in a matter of days. The latest version of DeepMind's AlphaFold, a deep-learning system that can accurately predict the structure of proteins to within the width of an atom, has cracked one of biology's grand challenges. According to John Moult, Professor at the University of Maryland, "It's the first use of AI to solve a serious problem,". In the experiment, DeepMind used a new deep learning architecture for AlphaFold that was able to interpret and compute the'spatial graph' of 3D proteins, predicting the molecular structure underpinning their folded configuration.

AI-equipped guide panels make Tokyo area train station debuts

The Japan Times

Electronic panels equipped with artificial intelligence debuted Tuesday at major train stations in the Tokyo area to provide tourist and transfer information for a trial period, with the railway operator aiming to use them to make up for a future labor shortage. East Japan Railway Co. set up 30 panels at six stations in Tokyo and neighboring Chiba Prefecture for the demonstration, which lasts through late January. As a measure against the coronavirus, users do not have to touch the panels directly to operate them and some can automatically measure a passenger's temperature. Available in Japanese, English, Chinese and Korean, the displays can respond to voice questions and finger movements. They are installed at Shinjuku, Shinagawa, Ikebukuro and Takanawa Gateway stations in Tokyo as well as at two locations in Chiba, Kaihinmakuhari and the Airport Terminal 2 station at Narita Airport.

Text Analysis & Mining Software for Semantic Enrichment


Retina API is the Natural Language Processing (NLP) and Text Analysis engine of 3RDi. It helps you see through the unstructured content and discover hidden facts powering an elevated search experience. It comes configured with a comprehensive set of thesauri and taxonomies and can also be integrated with your custom (and legacy) vocabularies. You get the benefit of a ready-to-use, yet, flexible semantic enrichment which can be adapted quickly to suit any specific domain.

Artificial Intelligence & Machine Learning – What Do They Mean?


There was a time when we heard terms like Artificial Intelligence and Machine Learning only in sci-fi movies. But today, technological advances have brought us to a point where businesses across verticals are not only talking about, but also implementing artificial intelligence and machine learning in everyday scenarios. AI is everywhere, from gaming stations to maintaining complex information at work. Computer Engineers and Scientists are working hard to impart intelligent behavior in the machines making them think and respond to real-time situations. AI has evolved from being a research topic to being at the early stages of enterprise adoption.