Bringing deep learning to life


Gaby Ecanow loves listening to music, but never considered writing her own until taking 6.S191 (Introduction to Deep Learning). By her second class, the second-year MIT student had composed an original Irish folk song with the help of a recurrent neural network, and was considering how to adapt the model to create her own Louis the Child-inspired dance beats. "It was cool," she says. "It didn't sound at all like a machine had made it." This year, 6.S191 kicked off as usual, with students spilling into the aisles of Stata Center's Kirsch Auditorium during Independent Activities Period (IAP).

How Impersonators Exploit Instagram to Generate Fake Engagement? Machine Learning

Impersonators on Online Social Networks such as Instagram are playing an important role in the propagation of the content. These entities are the type of nefarious fake accounts that intend to disguise a legitimate account by making similar profiles. In addition to having impersonated profiles, we observed a considerable engagement from these entities to the published posts of verified accounts. Toward that end, we concentrate on the engagement of impersonators in terms of active and passive engagements which is studied in three major communities including ``Politician'', ``News agency'', and ``Sports star'' on Instagram. Inside each community, four verified accounts have been selected. Based on the implemented approach in our previous studies, we have collected 4.8K comments, and 2.6K likes across 566 posts created from 3.8K impersonators during 7 months. Our study shed light into this interesting phenomena and provides a surprising observation that can help us to understand better how impersonators engaging themselves inside Instagram in terms of writing Comments and leaving Likes.

The future? AI-enabled cloud solutions for asset management


Never before have consumers had such an outstanding lineup of content offerings from which to choose – from award-winning original programming on OTT services like Netflix, to a galaxy of live-streamed and live-broadcast entertainment and sports events. First the good news: "I want my MTV." Some of us are old enough to remember that bygone slogan that expressed viewers' craving for music videos (back when MTV was all about music videos!) and well before the multiplatform internet age. That craving for all types of content has grown exponentially in the ensuing years, creating a potential gold mine of new opportunities for savvy media companies to develop lucrative new revenue streams. As media companies look for ways to realize that new revenue potential, they're running up against some real institutional barriers when they try to get their hands on the valuable content assets they need.

Google says its new chatbot Meena is the best in the world


Google has released a neural-network-powered chatbot called Meena that it claims is better than any other chatbot out there. Data slurp: Meena was trained on a whopping 341 gigabytes of public social-media chatter--8.5 times as much data as OpenAI's GPT-2. Google says Meena can talk about pretty much anything, and can even make up (bad) jokes. Why it matters: Open-ended conversation that covers a wide range of topics is hard, and most chatbots can't keep up. At some point most say things that make no sense or reveal a lack of basic knowledge about the world.

Predicting Sports Outcomes Using Python and Machine Learning


The purpose of this course is to teach about how to use Python and machine learning in order to predict sports outcomes. It takes you through through all the steps, from collecting data using a web crawler to making profitable bets based on your predicted results. The course is built around predicting tennis games, but the things taught can be extended to any sport, including team sports. The course includes: 1) Intro to Python and Pandas. This course is geared towards people that have some interest in data science and some experience in Python.

10. Introduction to Learning, Nearest Neighbors


Sign in to report inappropriate content. Instructor: Patrick Winston This lecture begins with a high-level view of learning, then covers nearest neighbors using several graphical examples. We then discuss how to learn motor skills such as bouncing a tennis ball, and consider the effects of sleep deprivation.

Table tennis-playing robot that can sense you getting frustrated and lower its skill level

Daily Mail - Science & tech

Japanese robotics company Omron and its table-tennis-playing bot are back at CES to serve up loads of fresh new tech. This year, though Omron may have reincarnated its crowd-pleasing table tennis bot, called Forpheus, the company managed to up the ante with a new emotional recognition system that gauges players' frustration level and their skill. In addition to being fun, Omron wants Forpheus to showcase its work in AI, computer vision and robotics. Its system, which watches players closely as they battle the bot in ping pong, has the capability of reading a players' face and even their heart rate and then interpreting that information to make inferences on skill and state-of-mind. Forpheus (pictured above) can reach to a volley using computer vision.

Joint Goal and Strategy Inference across Heterogeneous Demonstrators via Reward Network Distillation Machine Learning

Reinforcement learning (RL) has achieved tremendous success as a general framework for learning how to make decisions. However, this success relies on the interactive hand-tuning of a reward function by RL experts. On the other hand, inverse reinforcement learning (IRL) seeks to learn a reward function from readily-obtained human demonstrations. Yet, IRL suffers from two major limitations: 1) reward ambiguity - there are an infinite number of possible reward functions that could explain an expert's demonstration and 2) heterogeneity - human experts adopt varying strategies and preferences, which makes learning from multiple demonstrators difficult due to the common assumption that demonstrators seeks to maximize the same reward. In this work, we propose a method to jointly infer a task goal and humans' strategic preferences via network distillation. This approach enables us to distill a robust task reward (addressing reward ambiguity) and to model each strategy's objective (handling heterogeneity). We demonstrate our algorithm can better recover task reward and strategy rewards and imitate the strategies in two simulated tasks and a real-world table tennis task.

AI in the announcer's booth


I like to watch rugby, even though I know very little about it. They rightfully believe they're talking to people who watch rugby a lot, so they feel no need to address me, personally, with rugby-for-dummies spiels that might give me an appreciation for the game. But emerging technology could soon solve my problem. Some companies are working on AI that will generate custom sports commentary, which means I could potentially tune into a streaming rugby game and listen to a human-sounding, AI-driven robot commentator that already understands my level of rugby savvy. Maybe my robot commentator will patiently explain the difference between a blood bin and a tight head.

AI Knows If The Pitch Is On Target Before You Do


Pitching a baseball is about accuracy and speed. A swift ball on target is the goal, allowing the pitcher to strike out the batter. The system uses an NVIDIA Jetson AGX Xavier, fitted with a USB camera running at 100FPS. A Nerf tennis ball launcher is used to fire a ball towards the batter. Once triggered, the AI uses the camera to capture two successive images of the ball in flight.