Kris has presented us his takeaways from the SoFiE Summer School at University of Chicago: Machine Learning and Finance: The New Empirical Asset Pricing. He particulary focused his presentation on Empirical Asset Pricing via Machine Learning, a very recent paper (this version: July 21, 2018) exploring the use of different machine learning regressions on a given dataset of economic variables to predict future stock returns. Personal opinion: To be noticed, despite being a recent paper, they have still a rather outdated view of neural networks being very general (universal approximators) non-linear regressors rather than useful representation builders, the latter being used efficiently by linear models. A big claim of the paper is that one can reach a Sharpe ratio of 2 using these neural networks (once again only an old pyramidal architecture (1993) is tested) whereas linear models only achieve a Sharpe ratio of 0.5- using the same dataset. Bagging/Boosting trees methods lie somewhere in between. It's hard to evaluate and reproduce such papers.

So far, advances in AI are not bringing us real "intelligence." Rather, these advances are bringing us a key part of intelligence: prediction. This enables businesses to make predictions faster and more precisely to improve their business models and marketplace advantage. In this episode of Mind the Gap, Avi Goldfarb, an economist at the University of Toronto's Rotman School of Management and one of the authors of "Prediction Machines: The Simple Economics of Artificial Intelligence," will explain the economics of AI and how it can lead to better and cheaper predictions.

Every Act comes with a new battle pass, which offers rewards in exchange for experience points, gained by playing the game. The new Episode 2 battle pass will cost $10, and include three new skin lines, as well as player cards, gun buddies, titles and sprays. One of the new sets of skins, titled Infinity, will have three color variants, a novelty for weapons in the battle pass. Players who opt not to pay will still receive a few free rewards spaced throughout the pass.

Sign in to report inappropriate content. This is the second episode of my video series on applied machine learning. In this episode, we talk about the need for cross-validation and different types of cross-validation. We also see how one can implement a re-usable cross validation framework. In the end we are left with a cross validation framework that can be applied to almost all kinds of machine learning problem.

The automated home referred to as Smart Home is expected to offer fully customized services to its residents, reducing the amount of home labor, thus improving human beings' welfare. Service robots and Internet of Things (IoT) play the key roles in the development of Smart Home. The service provision with these two main components in a Smart Home environment requires: 1) learning and reasoning algorithms and 2) the integration of robot and IoT systems. Conventional computational intelligence-based learning and reasoning algorithms do not successfully manage dynamic changes in the Smart Home data, and the simple integrations fail to fully draw the synergies from the collaboration of the two systems. To tackle these limitations, we propose: 1) a stabilized memory network with a feedback mechanism which can learn user behaviors in an incremental manner and 2) a robot-IoT service provision framework for a Smart Home which utilizes the proposed memory architecture as a learning and reasoning module and exploits synergies between the robot and IoT systems. We conduct a set of comprehensive experiments under various conditions to verify the performance of the proposed memory architecture and the service provision framework and analyze the experiment results.

A percentage (usually around the 70%) that can be used for the training of the model, called training set. The rest of the data will play as the validation set and it will be used to evaluate the performance of the model when it receives data that has never seen. A percentage (usually around the 70%) that can be used for the training of the model, called training set. The rest of the data will play as the validation set and it will be used to evaluate the performance of the model when it receives data that has never seen. For more complex types of model, often a small percentage (usually 5% to 10% of all the datasets) is reserved for an additional evaluation of the performance, after that the model shows good results also on the validation set.

WATCH NOW: In the second episode of this docuseries, truck manufacturer PACCAR is taking advantage of AI to bring autonomy to its fleet, boosting both productivity and driver safety. ABOUT THE DOCUSERIES, "I AM AI": Who are today's leading AI innovators and how are they reshaping entire industries? This original docuseries explores the world's greatest artificial intelligence achievements and the people who are making them happen. Check back often for new episodes.

After an action-packed Season 12 premiere, Fox series "Bones" aired an episode with its regular case-of-the-week format. Season 12, episode 2 kicked off with the FBI investigating the death of tech genius Ian Goldberg. Goldberg owns a company called Social Cybernetics which makes robots that help kids suffering from autism. His body was found in the woods. The crowning glory of Goldberg's work is an artificial intelligence robot named AMI that can speak eight languages. The AMI is also a lot like Brennan (Emily Deschanel).

A couple of bickering trainers at a dog show lose track of their animals, who run into the woods and start feeding on a corpse. There is evidence all over the place, as well as indications of multiple scavengers. Based on tissue decomp, Saroyan puts time of death at about three to four days prior. Brennan estimates the victim was male based on the rugged linea aspera of the femur and in his 40s based on the degeneration of the femoral head. There is no sign of a struggle, but there is plastic fused to his wrist. Back at the Jeffersonian, Brennan and Daisy, who is now Dr. Wick, go over the body.

The Season 12 premiere finally answered questions about Zack (Eric Millegan) and revealed the identity of The Puppeteer. Now, the Jeffersonian can get back to solving grisly murders every week. In Season 12, episode 2, the team will have an interesting case in their hands. According to the synopsis (via SpoilerTV), the FBI discovers the body of man who created artificial intelligence. The promo reveals that the crime scene is teeming with evidence.