UC Berkeley – The Unsupervised Reinforcement Learning Benchmark

The shortcomings of supervised RL Reinforcement Learning (RL) is a powerful paradigm for solving many problems of interest in AI, such as controlling autonomous vehicles, digital assistants, and resource allocation to name a few. We’ve seen over the last five years that, when provided with an extrinsic reward function, RL agents can master very complex…

Latest from MIT : Nonsense can make sense to machine-learning models

For all that neural networks can accomplish, we still don’t really understand how they operate. Sure, we can program them to learn, but making sense of a machine’s decision-making process remains much like a fancy puzzle with a dizzying, complex pattern where plenty of integral pieces have yet to be fitted.  If a model was…

Latest from Google AI – Training Machine Learning Models More Efficiently with Dataset Distillation

Posted by Timothy Nguyen1, Research Engineer and Jaehoon Lee, Senior Research Scientist, Google Research For a machine learning (ML) algorithm to be effective, useful features must be extracted from (often) large amounts of training data. However, this process can be made challenging due to the costs associated with training on such large datasets, both in…

Latest from MIT : From “cheetah-noids” to humanoids

In November 2018, MIT Professor Sangbae Kim brought his mini cheetah robot onto “The Tonight Show’s” Tonight Show-botics segment. Much to the delight of host Jimmy Fallon, the mini cheetah did some yoga, got back up after falling, and executed a perfect backflip. Behind the stage, Benjamin Katz ’16, SM ’18 was remotely controlling the cheetah’s…

Latest from IBM Developer : Object tracking in video with OpenCV and Deep Learning

This code pattern is part of the Getting started with IBM Maximo Visual Inspection learning path. Level Topic Type 100 Introduction to computer vision Article 101 Introduction to IBM Maximo Visual Inspection Article 201 Build and deploy an IBM Maximo Visual Inspection model and use it in an iOS app Tutorial 202 Locate and count…

Latest from IBM Developer : Locate and count items with object detection

This code pattern is part of the Getting started with IBM Maximo Visual Inspection learning path. Level Topic Type 100 Introduction to computer vision Article 101 Introduction to IBM Maximo Visual Inspection Article 201 Build and deploy an IBM Maximo Visual Inspection model and use it in an iOS app Tutorial 202 Locate and count…

Latest from IBM Developer : Validate computer vision deep learning models

This code pattern is part of the Getting started with IBM Maximo Visual Inspection learning path. Level Topic Type 100 Introduction to computer vision Article 101 Introduction to IBM Maximo Visual Inspection Article 201 Build and deploy an IBM Maximo Visual Inspection model and use it in an iOS app Tutorial 202 Locate and count…

Latest from MIT Tech Review – To accelerate business, build better human-machine partnerships

Businesses that want to be digital leaders in their markets need to embrace automation, not only to augment existing capabilities or to reduce costs but to position themselves to successfully maneuver the rapid expansion of IT demand ushered in through digital innovation. “It’s a scale issue,” says John Roese, global chief technology officer at Dell…

Latest from Google AI – Interpretable Deep Learning for Time Series Forecasting

Posted by Sercan O. Arik, Research Scientist and Tomas Pfister, Engineering Manager, Google Cloud Multi-horizon forecasting, i.e. predicting variables-of-interest at multiple future time steps, is a crucial challenge in time series machine learning. Most real-world datasets have a time component, and forecasting the future can unlock great value. For example, retailers can use future sales…