We propose a novel approach to train a multi-modal policy from mixed demonstrations without their behavior labels. We develop a method to discover the latent factors of variation in the demonstrations. Specifically, our method is based on the variational autoencoder with a categorical latent variable. The encoder infers discrete latent factors corresponding to different behaviors from demonstrations. The decoder, as a policy, performs the behaviors accordingly. Once learned, the policy is able to reproduce a specific behavior by simply conditioning on a categorical vector. We evaluate our method on three different tasks, including a challenging task with high-dimensional visual inputs. Experimental results show that our approach is better than various baseline methods and competitive with a multi-modal policy trained by ground truth behavior labels.

Understanding the community conditions that best support universal access and improved childhood outcomes allows ultimately to improve decision-making in the areas of planning and investment across the early stages of childhood development. Here we describe two different data-driven approaches to visualizing the lived experiences of children throughout the City of Surrey, combining data derived from both public and private sources. In one approach, we find specifically that the Early Development Instrument measuring childhood vulnerabilities across varying domains can be used to cluster neighborhoods, and that census variables can help explain similarities between neighborhoods within these clusters. In our second approach, we use program registration data from the City of Surrey's Community and Recreation Services Division. We also find a critical age of entry and exit for each program related to early childhood development and beyond, and find that certain neighborhoods and recreational programs have larger retention rates than others. This report details the journey of using data to tell the story of these neighborhoods, and provides a lens to which community initiatives can be strategically crafted through their use.

In autonomous embedded systems, it is often vital to reduce the amount of actions taken in the real world and energy required to learn a policy. Training reinforcement learning agents from high dimensional image representations can be very expensive and time consuming. Autoencoders are deep neural network used to compress high dimensional data such as pixelated images into small latent representations. This compression model is vital to efficiently learn policies, especially when learning on embedded systems. We have implemented this model on the NVIDIA Jetson TX2 embedded GPU, and evaluated the power consumption, throughput, and energy consumption of the autoencoders for various CPU/GPU core combinations, frequencies, and model parameters. Additionally, we have shown the reconstructions generated by the autoencoder to analyze the quality of the generated compressed representation and also the performance of the reinforcement learning agent. Finally, we have presented an assessment of the viability of training these models on embedded systems and their usefulness in developing autonomous policies. Using autoencoders, we were able to achieve 4-5 $\times$ improved performance compared to a baseline RL agent with a convolutional feature extractor, while using less than 2W of power.

Abstract: We review computational and robotics models of early language learning and development. We first explain why and how these models are used to understand better how children learn language. We argue that they provide concrete theories of language learning as a complex dynamic system, complementing traditional methods in psychology and linguistics. We review different modeling formalisms, grounded in techniques from machine learning and artificial intelligence such as Bayesian and neural network approaches. We then discuss their role in understanding several key mechanisms of language development: cross-situational statistical learning, embodiment, situated social interaction, intrinsically motivated learning, and cultural evolution. We conclude by discussing future challenges for research, including modeling of large-scale empirical data about language acquisition in real-world environments. Language involves a multitude of components interacting in complex ways in parallel ...

Though Elon Musk has famously warned humanity about the dangers of artificial intelligence, his shareholders might be well-served by having an algorithm on Tesla's board of directors. In recent years, Tesla has become a cautionary tale for how difficult it is for part-time directors to oversee charismatic, strong-willed CEOs--especially ones who are the founding visionaries of their companies. Given how Elon Musk has landed the company in hot water with the Securities and Exchange Commission with his erratic tweets and mocking disregard for the regulatory regime dictating the proper behavior of a publicly traded company, it's little wonder that Tesla's board has been accused of being "asleep at the wheel." Perhaps their seeming unwillingness to rein him in is due to the Tesla directors' personal loyalty to Musk. Or maybe they simply don't want to spend the time to "preapprove" Musk's tweets about the company, especially with the less conventional hours and fast pace the CEO keeps.

In 1891, when the German biologist Hans Driesch split two-cell sea urchin embryos in half, he found that each of the separated cells then gave rise to its own complete, albeit smaller, larva. Somehow, the halves "knew" to change their entire developmental program: At that stage, the blueprint for what they would become had apparently not yet been drawn out, at least not in ink. Original story reprinted with permission from Quanta Magazine, an editorially independent publication of the Simons Foundation whose mission is to enhance public understanding of science by covering research developments and trends in mathematics and the physical and life sciences. Since then, scientists have been trying to understand what goes into making this blueprint, and how instructive it is. It's now known that some form of positional information makes genes variously switch on and off throughout the embryo, giving cells distinct identities based on their location.

Thinking about the fantastic pie-in-the-sky future is always a fun exercise. I, too, want a self-driving car. But some weeks, it's clear everyone needs to come down to earth. This was one of them. Tesla sued two other electric vehicle companies focusing on self-driving for trade secret theft, proving that building this tech will be a grind.

The artificial intelligence industry is often criticized for failing to think through the social repercussions of its technology--think instituting gender and racial bias in everything facial-recognition software to hiring algorithms. On Monday (March 18), Stanford University launched a new institute meant to show its commitment to addressing concerns over the industry's lack of diversity and intersectional thinking. The Institute for Human-Centered Artificial Intelligence (HAI), which plans to raise $1 billion from donors to fund its initiatives, aims to give voice to professionals from fields ranging from the humanities and the arts to education, business, engineering, and medicine, allowing them to weigh in on the future of AI. "Now is our opportunity to shape that future by putting humanists and social scientists alongside people who are developing artificial intelligence," Stanford president Marc Tessier-Lavigne declared in a press release. But in trying to address AI's blind spots, the institute has been accused of replicating its biases. Of the 121 faculty members initially announced as part of the institute, more than 100 appeared to be white, and a majority were male.

The patentability of artificial intelligence (AI) has been increasingly scrutinized in light of the surge in AI technology development and the ambiguity regarding the interpretation of software-related patents. The Federal Circuit has gradually refined the criteria for determining subject matter eligibility for software-related patents, and based in part on such jurisprudence, earlier this year the U.S. Patent and Trademark Office (USPTO) released revised guidance on examining patent subject matter eligibility under 35 U.S.C. §101. See 2019 Revised Patent Subject Matter Eligibility Guidance, 84 Fed. Considering the advances in AI technology and intellectual property law, how do these recent developments shape the outlook of AI patentability?

First, a couple of pointers to keep in mind when searching for datasets. Kaggle: A data science site that contains a variety of externally contributed interesting datasets. You can find all kinds of niche datasets in its master list, from ramen ratings to basketball data to and even seattle pet licenses. Although the data sets are user-contributed, and thus have varying levels of cleanliness, the vast majority are clean. VisualData: Discover computer vision datasets by category, it allows searchable queries.