Vincross, the company behind the six-legged robot Hexa, said on Tuesday that it's picked up $10 million in a Series A funding round led by Lenovo Capital, the startup fund managed by Lenovo Group. Returning investor GGV Capital and newcomer Seekdource Capital also participated. The company declined to disclose its latest valuation but said the proceeds will go towards research and development as well as new product lines. Neuroscience and artificial intelligence researcher Tianqi Sun started Vincross in Beijing back in 2016 when he raised $220,000 for Hexa on Kickstarter. At the time the insectile, programmable robot had separated itself from the horde of humanoids on the market by billing itself as the first robot that can climb stairs, making it suitable for firefighting and other rescue tasks.

Your customers want the best app experience you can provide. Add artificial intelligence (AI) capabilities to your apps that make customers notice and choose your offerings over those of the competition. Read our e-book, Differentiate Your Apps with Intelligent Technology: How Software Vendors are Using AI to Bring Greater Value to Customers, to find out how you can include AI in your apps in ways that delight your customers--and increase your margins as a result. Inspect and categorize massive data stores to make information searchable and accessible. Create engaging, interactive training environments using enhanced virtual and augmented reality.

Robots are progressively being utilized to teach students in the classroom for various subjects crosswise over science, maths and language. Despite the fact that grown-ups may rapidly end up disillusioned with machines that aren't exceptionally insightful or don't talk more than scripted sentences, kids are liable to chat with, tune in to and generally treat even fundamental robots as social creatures, says Tony Belpaeme, a social roboticist at Ghent University in Belgium. Scientists like Breazeal and Belpaeme are attempting to use that association to make robots connect with children as coaches and peep learners. However, according to a research, while students appreciate learning with robots, tutors are somewhat hesitant to utilize them in the classroom. In our examination, which saw staff and students connect with the Nao humanoid robot, tutors believe they were more incredulous of robots being deployed into the classroom.

The popular Data Science competition website Kaggle has an ongoing competition to solve the problem of earthquake prediction. Given a dataset of seismographic activity from a laboratory simulation, participants are asked to create a predictive model for earthquakes. In this video, I'll attempt the challenge as a way to teach 3 concepts; the Data Science mindset, Categorical Boosting, and Support Vector Regression models. I'll be coding this using python from start to finish in the online Google colab environment. Thats what keeps me going.

The members of the Global University Leaders Forum community convened at the World Economic Forum Annual Meeting 2019 to discuss their role in our ever-changing world. Here are six topics that were top of the agenda as the members considered the future of the university and its role in society. Today data is omnipresent and often overwhelming. By way of example, Domo's Data Never Sleeps 6.0 reported that in 2018 Google conducted an average 3.8 million searches per minute. Though not all graduates will enter data-related fields, universities are starting to work towards increasing data literacy in their student body by adding data science courses and challenges for social science majors so that graduates can effectively communicate with their data-oriented peers and co-workers.

Microsoft's latest acquisition shows how combining pedagogy and technology can dramatically improve learning outcomes. "Today's students will graduate into a world that will be dramatically different – and changing faster than ever. They will enter a workforce where job functions, roles and even categories will be significantly altered, and will face social and global challenges beyond what we can imagine today," says Steve Liffick, General Manager of Education Strategy and Platforms at Microsoft. Research recently conducted by the company – "The class of 2030 and life-ready learning: The technology imperative" – concluded that student-centric approaches will be critical to achieving this. We need to radically change our approach if we are to prepare those students for the increasingly creative, collaborative, digitally-infused world they will enter as adults.

When I was in middle-school, I was always most excited about my painting class. Both myself and my teacher were quite aware of my lack of talent, but it made me really happy to play with colors. I didn't make the most beautiful paintings, I didn't get the best grades in class, but I was mesmerized by the way I could mix different colors and use them to create something on a canvas. When I got a little bit older and went to high-school, the painting classes were replaced with a lot of math and programming subjects that I wasn't as excited about. I always missed having a class where I could create something that was visually interesting.

Many machine learning algorithms represent input data with vector embeddings or discrete codes. When inputs exhibit compositional structure (e.g. objects built from parts or procedures from subroutines), it is natural to ask whether this compositional structure is reflected in the the inputs' learned representations. While the assessment of compositionality in languages has received significant attention in linguistics and adjacent fields, the machine learning literature lacks general-purpose tools for producing graded measurements of compositional structure in more general (e.g. vector-valued) representation spaces. We describe a procedure for evaluating compositionality by measuring how well the true representation-producing model can be approximated by a model that explicitly composes a collection of inferred representational primitives. We use the procedure to provide formal and empirical characterizations of compositional structure in a variety of settings, exploring the relationship between compositionality and learning dynamics, human judgments, representational similarity, and generalization.

We study the dynamic regret of a new class of online learning problems, in which the gradient of the loss function changes continuously across rounds with respect to the learner's decisions. This setup is motivated by the use of online learning as a tool to analyze the performance of iterative algorithms. Our goal is to identify interpretable dynamic regret rates that explicitly consider the loss variations as consequences of the learner's decisions as opposed to external constraints. We show that achieving sublinear dynamic regret in general is equivalent to solving certain variational inequalities, equilibrium problems, and fixed-point problems. Leveraging this identification, we present necessary and sufficient conditions for the existence of efficient algorithms that achieve sublinear dynamic regret. Furthermore, we show a reduction from dynamic regret to both static regret and convergence rate to equilibriums in the aforementioned problems, which allows us to analyze the dynamic regret of many existing learning algorithms in few steps.

We consider the problem of learning from sparse and underspecified rewards, where an agent receives a complex input, such as a natural language instruction, and needs to generate a complex response, such as an action sequence, while only receiving binary success-failure feedback. Such success-failure rewards are often underspecified: they do not distinguish between purposeful and accidental success. Generalization from underspecified rewards hinges on discounting spurious trajectories that attain accidental success, while learning from sparse feedback requires effective exploration. We address exploration by using a mode covering direction of KL divergence to collect a diverse set of successful trajectories, followed by a mode seeking KL divergence to train a robust policy. We propose Meta Reward Learning (MeRL) to construct an auxiliary reward function that provides more refined feedback for learning. The parameters of the auxiliary reward function are optimized with respect to the validation performance of a trained policy. The MeRL approach outperforms our alternative reward learning technique based on Bayesian Optimization, and achieves the state-of-the-art on weakly-supervised semantic parsing. It improves previous work by 1.2% and 2.4% on WikiTableQuestions and WikiSQL datasets respectively.