Collaborating Authors

Microsoft launches a drag-and-drop machine learning tool – TechCrunch


Microsoft today announced three new services that all aim to simplify the process of machine learning. These range from a new interface for a tool that completely automates the process of creating models, to a new no-code visual interface for building, training and deploying models, all the way to hosted Jupyter-style notebooks for advanced users. Getting started with machine learning is hard. Even to run the most basic of experiments takes a good amount of expertise. All of these new tools greatly simplify this process by hiding away the code or giving those who want to write their own code a pre-configured platform for doing so.

TiVo is developing a new set-top box user interface that can also run on top of Android


You might still think of TiVo as a DVR company, but this year a different strategy is starting to emerge. TiVo didn't bring any consumer hardware to CES 2017; instead, the company showed off a brand-new TiVo interface--first announced last September--that tries to predict what you might watch based on past viewing patterns. That new interface should become available for the entire TiVo customer base this year, says Paul Stathacopoulos, TiVo's vice president of strategy. It can also run on Android, paving the way for new streaming devices with TiVo's recommendations, browsing experience, and search on top. TiVo's emphasis on software, rather than hardware, at CES shouldn't be a huge surprise.



Each class in the config has name parameter, which is its registered codename and can have any other parameters, repeating its __init__() method arguments. Default values of __init__() arguments will be overridden with the config values during class instance initialization. DatasetReader class reads data and returns it in a specified format. Dataset forms needed sets of data ('train', 'valid', 'test') and forms data batches. Vocab is a trainable class, which forms and serialize vocabs.

Designing a Python interface for machine learning engineering


In order to do machine learning engineering, a model must first be deployed, in most cases as a prediction API. In order to make this API work in production, model serving infrastructure must first be built. This includes load balancing, scaling, monitoring, updating, and much more. At first glance, all of this work seems familiar. Web developers and DevOps engineers have been automating microservice infrastructure for years now.

The First Step Towards Responsible AI Needs To Be About People Not Strategy


I was recently consulting for an organisation that was looking to implement a framework to govern the implementation of Artificial Intelligence (AI) technologies. Like many organisations in their sector, they had been running various'lab' experiments for some time, and had seen positive results; but there was still something holding them back from wholesale investment. A major consulting firm had encouraged them to'accelerate' their innovation by using a framework to govern the roll-out. I asked them where they felt it needed more focus, and they responded saying that it felt somewhat vanilla, a re-hashing of any-old IT project management best practice. "Surely there is something different about AI", they asked?