Measuring reading effort is useful for practical purposes such as designing learning material and personalizing text comprehension environment. We propose a quantification of reading effort by measuring the complexity of eye-movement patterns of readers. We call the measure Scanpath Complexity. Scanpath complexity is modeled as a function of various properties of gaze fixations and saccades- the basic parameters of eye movement behavior. We demonstrate the effectiveness of our scanpath complexity measure by showing that its correlation with different measures of lexical and syntactic complexity as well as standard readability metrics is better than popular baseline measures based on fixation alone.

In order for reinforcement learning systems to learn quickly in vast action spaces such as the space of all possible pieces of text or the space of all images, leveraging human intuition and creativity is key. However, a human-designed action space is likely to be initially imperfect and limited; furthermore, humans may improve at creating useful actions with practice or new information. Therefore, we propose a framework in which a human adds actions to a reinforcement learning system over time to boost performance. In this setting, however, it is key that we use human effort as efficiently as possible, and one significant danger is that humans waste effort adding actions at places (states) that aren't very important. Therefore, we propose Expected Local Improvement (ELI), an automated method which selects states at which to query humans for a new action. We evaluate ELI on a variety of simulated domains adapted from the literature, including domains with over a million actions and domains where the simulated experts change over time. We find ELI demonstrates excellent empirical performance, even in settings where the synthetic "experts" are quite poor.

A machine learning algorithm designed to teach computers how to recognize photos, speech patterns, and hand-written digits has now been applied to a vastly different set of data: identifying phase transitions between states of matter. This new research, published today in Nature Physics by two Perimeter Institute researchers, was built on a simple question: could industry-standard machine learning algorithms help fuel physics research? To find out, former Perimeter Institute postdoctoral fellow Juan Cassasquilla and Roger Melko, an Associate Faculty member at Perimeter and Associate Professor at the University of Waterloo, repurposed Google's TensorFlow, an open-source software library for machine learning, and applied it to a physical system. Melko says they didn't know what to expect. "I thought it was a long shot," he admits. Using gigabytes of data representing different state configurations created using simulation software on supercomputers, Carrasquilla and Melko created a large collection of "images" to introduce into the machine learning algorithm (also known as a neural network).

Yuval Noah Harari might be Silicon Valley's favorite historian. His last book, Sapiens: A Brief History of Humankind, which detailed the entirety of human history and how Homo Sapiens came to dominate the Earth, was blurbed by President Barack Obama and Bill Gates, and Mark Zuckerberg recommended it for his book club. And more than 100,000 students have taken Harari's online course. In his new book, Homo Deus: A Brief History of Tomorrow, Harari looks forward and hazards a few guesses on what comes next for humanity. These next chapters in our history range from the utopian to the horrific, he says.

If we have an initial learning rate high enough and a suitable decay factor for exponentially decaying the learning rate over a certain number of epoch, is it still need for us to manually explore the learning rate? Because if all goes well I believe the learning rate can automatically be sampled over a huge range of epoch. However, if we start off with a less than optimal learning rate, assuming the loss does not diverge to infinity, would the loss be less optimal than we have started with the optimal learning rate, even if we could reach the optimal learning rate through decaying the initial learning rate over time? Does the answer differ for a convex/non-convex loss? Specifically for deep learning problems, is an exponential decaying learning rate able to sample the learning rate better than done manually?

Chatbots aren't as "inhuman" as you might believe them to be. Chatbots cannot be human, but they can think and respond to queries like humans do. This is happening in a medium (text messages) which is emerging as the next big platform for information exchange after voice. With advances in Artificial Intelligence (AI) and Natural Language Processing (NLP) capabilities, machine learning code can now understand queries just like humans do. More importantly the code learns from every interaction that it does and grows its skills to handle further conversations!

Organizations create style guides to capture the rationale of their design decisions and help other teams build great experiences. You might have read gov.UK's service manual or the U.S. Digital Services Playbook. I wanted to do the same for chatbots built on the Facebook's Messenger platform. At Sure, we are creating an online assistant that helps you find food and drinks that are better for you and the planet. It is still very early days for bots, so I wanted to take the opportunity to share some of our early learnings.

These videos are part of an online course, Intro to Machine Learning. Check out the course here: https://www.udacity.com/course/ud120. This course was designed as part of a program to help you and others become a Data Analyst. You can check out the full details of the program here: https://www.udacity.com/course/nd002. These videos are part of an online course, Intro to Machine Learning.

Unless you've recently graduated from one of the new Data Science courses that have been popping up online and in various universities around the world, then becoming a Data Scientist was most likely slightly accidental and was more about the journey than the destination. I started out as a physicist and had a strong mathematical grounding, but I had a passion for medicine. After completing my bachelor's degree I took a master's degree in medical physics. This is where I gained an appreciation for the importance of image analysis and the role that data plays in medicine. I created a virtual model of a human torso by segmenting images from the Visible Human Project.

In addition to targeting customers based on inferred wants and needs, a compelling facet of personalization is something Forrester Research identifies as "Operationalizing Emotion", which alludes to customers making purchasing decisions based as much (or more) on emotional experiences than on rational conclusions. Today's market is all the more risky for companies that don't provide a stellar customer experience from start to finish, and it's becoming more common for businesses to suffer longer-term revenue losses for a single negative experience, whether directly experienced by the customer or based on empathy for others' experiences. A quick and personalized response to any customer dissatisfaction seems almost an essential application for businesses that want to stay afloat for the long-haul.