Training a neural network or large deep learning model is a difficult optimization task. The classical algorithm to train neural networks is called stochastic gradient descent. It has been well established that you can achieve increased performance and faster training on some problems by using a learning rate that changes during training. In this post you will discover how you can use different learning rate schedules for your neural network models in Python using the Keras deep learning library. Using Learning Rate Schedules for Deep Learning Models in Python with Keras Photo by Columbia GSAPP, some rights reserved.

Back in 1997, Andy Grove, then chief executive officer of Intel, became one of the first corporate titans to embrace the teachings of Harvard Business School professor Clayton Christensen. Sensing that Intel might be undercut by PC chip rivals with cheaper wares, Grove invited Christensen to speak to his team about industrial leaders of the past who had waited too long to address emerging threats. Within a few quarters, Intel had brought out a line of lower-end Celeron chips for PCs, which pretty much smashed the dreams of Intel wannabes such as Advanced Micro Devices. Intel is no longer a case study in adaptability. On the contrary, it has whiffed in the market for mobile chips used in smartphones and tablets, by far the largest new opportunity for chip makers in the past 10 years.

If you walk down the street and see two people meeting in front of a café, you know they'll shake hands or even hug a few seconds later, depending on how close their relationship is. Left: still frame given to the algorithm which had to predict what happened next. MIT used deep-learning algorithms -- neural networks that teach computers to find patterns by themselves from an ocean of data -- to build an artificial intelligence which can predict what action will occur next, starting from nothing but a still frame. Each of these networks was programmed to classify an action as either a hug, handshake, high-five, or kiss. These networks are then merged to predict what happens next.

Most accurate recommender systems are black-box models, hiding the reasoning behind their recommendations. Yet explanations have been shown to increase the user's trust in the system in addition to providing other benefits such as scrutability, meaning the ability to verify the validity of recommendations. This gap between accuracy and transparency or explainability has generated an interest in automated explanation generation methods. Restricted Boltzmann Machines (RBM) are accurate models for CF that also lack interpretability. In this paper, we focus on RBM based collaborative filtering recommendations, and further assume the absence of any additional data source, such as item content or user attributes. We thus propose a new Explainable RBM technique that computes the top-n recommendation list from items that are explainable. Experimental results show that our method is effective in generating accurate and explainable recommendations.

MIT researchers have trained a set of connected computer systems to understand body language patterns so that it can guess how two people will interact. MIT researchers have trained a set of connected computer systems to understand body language patterns so that it can guess how two people will interact. Sometimes a lean is just a lean and sometimes a lean leads to a kiss. A new deep-learning algorithm can predict the difference. MIT researchers have trained a set of connected computer systems to understand body language patterns so that it can guess how two people will interact.

A remarkable feature of human and animal intelligence is the ability to autonomously acquire new behaviors. This research is concerned with designing algorithms that aim to bring this ability to robots and simulated characters. Levine will describe a class of guided policy search algorithms that tackle this challenge by transforming the task of learning control policies into a supervised learning problem, with supervision provided by simple, efficient trajectory-centric methods.

This is not a fiction, this is not just an idea, this is the future. Join us to understand the limitless possibilities when geospatial big data meets deep learning and how it will shape a smarter world.

Scientists at Insilico Medicine have developed a new drug-discovery engine that they say is capable of predicting therapeutic use, toxicity, and adverse effects of thousands of molecules, and they plan to reveal it at the Re-Work Machine Intelligence Summit in Berlin, June 29–30. Drug discovery takes decades, with high failure rates. Among the reasons: irreproducible experiments with poor choice of animal models and inability to translate the results from animal models directly to humans, the wide variety of diseases, and communication difficulties between scientists, managers, venture capitalists, pharmaceutical companies and regulators. And perhaps the biggest problem: the slow-paced, bureaucratic culture in the pharmaceutical industry, the researchers note. Insilico Medicine says it aims to address these reasons by developing "multimodal deep-learned and parametric biomarkers," as well as multiple drug-scoring pipelines for drug discovery and drug repurposing, and hypothesis and lead generation.

The nonprofit group linked to Elon Musk and other Silicon Valley tech paragons wants to start with the basics -- household chores. Its No. 2 goal -- No. 1 being a decidedly more prosaic vow to measure its own progress in advancing artificial intelligence -- is to build a household robot, one to "perform basic housework," OpenAI said in a blog post this week. Sure, such a thing would be welcomed the world over. But what makes this future housemaid robot rank so highly among the group's ideas and experiments is that robotics in general is a "good testbed for many challenges in (artificial intelligence)," Open AI says. OpenAI dubs itself "a non-profit artificial intelligence research company" with the goal of advancing AI in ways most likely to benefit humanity, all the while uninhibited by the need to generate a profit.

Artificial intelligence nonprofit OpenAI, funded by some of the biggest names in Silicon Valley, announced its major goals today, which include the creation of a "general purpose" robot and a natural language processing chatbot. "We're working to enable a physical robot (off-the-shelf; not manufactured by OpenAI) to perform basic housework," the nonprofit said in a blog post authored by OpenAI Research Director Ilya Sutskever, OpenAI CTO Greg Brockman, Sam Altman, and Elon Musk. An agent, a system able to respond to user input like a bot, will be built with "the ability to carry a conversation, the ability to fully understand a document, and the ability to follow complex instructions in natural language." Another intelligent agent will be made to win games. Finally, OpenAI plans to identify or create a metric to measure its progress.