Regularization does NOT improve the performance on the data set that the algorithm used to learn the model parameters (feature weights). However, it can improve the generalization performance, i.e., the performance on new, unseen data, which is exactly what we want. In intuitive terms, we can think of regularization as a penalty against complexity. Increasing the regularization strength penalizes "large" weight coefficients -- our goal is to prevent that our model picks up "peculiarities," "noise," or "imagines a pattern where there is none." Again, we don't want the model to memorize the training dataset, we want a model that generalizes well to new, unseen data. In more specific terms, we can think of regularization as adding (or increasing the) bias if our model suffers from (high) variance (i.e., it overfits the training data).

A new computer prototype called a "memcomputer" works by mimicking the human brain, and could one day perform notoriously complex tasks like breaking codes, scientists say. These new, brain-inspired computing devices also could help neuroscientists better understand the workings of the human brain, researchers say. In a conventional microchip, the processor, which executes computations, and the memory, which stores data, are separate components. In contrast, Massimiliano Di Ventra, a theoretical physicist at the University of California, San Diego, and his colleagues are building "memcomputers," made up of "memprocessors," that both process and store data. This setup mimics the neurons that make up the human brain, with each neuron serving as both the processor and the memory. The building blocks of memcomputers were first theoretically predicted in the 1970s, but they were manufactured for the first time in 2008.

Today, I'm going to explain in plain English the top 10 most influential data mining algorithms as voted on by 3 separate panels in this survey paper. Once you know what they are, how they work, what they do and where you can find them, my hope is you'll have this blog post as a springboard to learn even more about data mining. In order to do this, C4.5 is given a set of data representing things that are already classified. A classifier is a tool in data mining that takes a bunch of data representing things we want to classify and attempts to predict which class the new data belongs to. Sure, suppose a dataset contains a bunch of patients.

Predicting what will happen in the future is challenging. Researchers from MIT's Computer Science and Artificial Intelligence Laboratory developed an algorithm that can predict whether two individuals will hug, kiss, shake hands or slap five in the next scene. Using a Tesla K40 GPU with the cuDNN-accelerated Caffe deep learning framework, the researchers trained their network on 600 hours of prime-time television shows including The Office and Desperate Housewives. When predicting which of the four actions the person would perform one second later, the algorithm correctly predicted the action more than 43 percent of the time – and humans who have been watching TV for years were only able to predict the next action with 71 percent accuracy. In their second study, the algorithm was shown frames from a video and asked it to predict what object will appear five seconds later.

HOW HAS ARTIFICIAL intelligence, associated with hubris and disappointment since its earliest days, suddenly become the hottest field in technology? The term was coined in a research proposal written in 1956 which suggested that significant progress could be made in getting machines to "solve the kinds of problems now reserved for humans…if a carefully selected group of scientists work on it together for a summer". That proved to be wildly overoptimistic, to say the least, and despite occasional bursts of progress, AI became known for promising much more than it could deliver. Researchers mostly ended up avoiding the term, preferring to talk instead about "expert systems" or "neural networks". The rehabilitation of "AI", and the current excitement about the field, can be traced back to 2012 and an online contest called the ImageNet Challenge.

In machine learning often a tradeoff must be made between accuracy and intelligibility: the most accurate models usually are not very intelligible (e.g., random forests, boosted trees, and neural nets), and the most intelligible models usually are less accurate (e.g., linear or logistic regression). This tradeoff often limits the accuracy of models that can be applied in mission-critical applications such as healthcare where being able to understand, validate, edit, and trust a learned model is important. We have developed a learning method based on generalized additive models (GAMs) that is often as accurate as full complexity models, but remains as intelligible as linear/logistic regression models. In the talk I'll present two case studies where these high-performance generalized additive models (GA2Ms) are applied to healthcare problems yielding intelligible models with state-of-the-art accuracy. In the pneumonia risk prediction case study, the intelligible model uncovers surprising patterns in the data that previously had prevented complex learned models from going to clinical trial, but because it is intelligible and modular allows these patterns to easily be recognized and removed.

The state-of-the-art in object recognition has undergone dramatic changes in the last 20 years. In this talk, I will review the progression of the field and discuss why various approaches both succeeded and failed. The talk will cover visual recognition from the early 90's, including handwritten digit and face detection, to the current state-of-the-art in deep learning applied to object categorization. Algorithms will be explained at an intuitive level. The talk is aimed at the non-expert in computer vision with some knowledge of machine learning.

XPRIZE has announced that registration is now open and guidelines are available for the 5 million IBM Watson AI XPRIZE, a four-year global competition challenging teams to develop and demonstrate how humans can collaborate with powerful artificial intelligence (AI) technologies to tackle the world's greatest challenges. The AI competition is XPRIZE's first open challenge where teams will define their own goals and create AI applications that solve some of humanity's most pressing challenges in areas such as healthcare, education, energy & environment, global development and exploration. "In the coming decade, as XPRIZE strives to achieve its impact mission through incentive competitions and crowd-sourcing, we see tremendous opportunity in this emerging generation of problem solvers to use AI to solve humanity's grandest challenges," said Marcus Shingles, CEO of XPRIZE. "The IBM Watson AI XPRIZE is intended to promote and progress the notion of'AI for impact' among the global bold innovator crowd, both the established community of practitioners, as well as encourage newcomers to experiment and ultimately demonstrate how AI can be used as a tool for good." Teams have until December 1, 2016 to register through the XPRIZE website for the four-year competition, and then will have until March 1, 2017 to submit a detailed development and testing plan for their proposed solution.

One early morning in March 2011, Albert Chretien and his wife, Rita, loaded their Chevrolet Astro van and drove away from their home in Penticton, British Columbia. Their destination was Las Vegas, where Albert planned to attend a trade show. Rather than stick to the most direct route, they decided to take a scenic road less travelled, Idaho State Highway 51. The Chretiens figured there had to be a turnoff from Idaho 51 that would lead them east to US Route 93 all the way to Vegas. Albert and Rita had known each other since high school. During their 38 years of marriage, they had rarely been apart. They worked together, managing their own small excavation business.

As artificial intelligence gains popularity, designers will need to adapt. Here's how to get started. It seems like everyone wants to invest in artificial intelligence (AI). And it's not just the tech giants: USAA is using AI to protect its users from identity theft and Under Armour has connected its health app, MyFitnessPal, to IBM Watson so users can get a more thorough read of their health. AI is already a 15 billion dollar industry, according to the MIT Technology Review, with more than 2,600 companies developing their own tech, and the value of AI isreported to rise to over 70 billion by 2020.