We consider the problem of efficiently approximating and encoding high-dimensional data sampled from a probability distribution $\rho$ in $\mathbb{R}^D$, that is nearly supported on a $d$-dimensional set $\mathcal{M}$ - for example supported on a $d$-dimensional Riemannian manifold. Geometric Multi-Resolution Analysis (GMRA) provides a robust and computationally efficient procedure to construct low-dimensional geometric approximations of $\mathcal{M}$ at varying resolutions. We introduce a thresholding algorithm on the geometric wavelet coefficients, leading to what we call adaptive GMRA approximations. We show that these data-driven, empirical approximations perform well, when the threshold is chosen as a suitable universal function of the number of samples $n$, on a wide variety of measures $\rho$, that are allowed to exhibit different regularity at different scales and locations, thereby efficiently encoding data from more complex measures than those supported on manifolds. These approximations yield a data-driven dictionary, together with a fast transform mapping data to coefficients, and an inverse of such a map. The algorithms for both the dictionary construction and the transforms have complexity $C n \log n$ with the constant linear in $D$ and exponential in $d$. Our work therefore establishes adaptive GMRA as a fast dictionary learning algorithm with approximation guarantees. We include several numerical experiments on both synthetic and real data, confirming our theoretical results and demonstrating the effectiveness of adaptive GMRA.

We propose an algorithm for meta-learning that is model-agnostic, in the sense that it is compatible with any model trained with gradient descent and applicable to a variety of different learning problems, including classification, regression, and reinforcement learning. The goal of meta-learning is to train a model on a variety of learning tasks, such that it can solve new learning tasks using only a small number of training samples. In our approach, the parameters of the model are explicitly trained such that a small number of gradient steps with a small amount of training data from a new task will produce good generalization performance on that task. In effect, our method trains the model to be easy to fine-tune. We demonstrate that this approach leads to state-of-the-art performance on two few-shot image classification benchmarks, produces good results on few-shot regression, and accelerates fine-tuning for policy gradient reinforcement learning with neural network policies.

Good teachers meet their students where they are, and they adapt their methods accordingly. Tutoring systems, language learning apps, and educational games are all designed to change our mental abilities. It's when we consider what it takes to change mental abilities or behaviors that things start to get interesting. It isn't just that people adapt to technology, and that technology adapts to people.

In this article, we revisit the most fundamental statistics theorem, talking in layman terms. We investigate a special but interesting and useful case, which is not discussed in textbooks, data camps, or data science classes. This article is part of a series about off-the-beaten-path data science and mathematics, offering a fresh, original and simple perspective on a number of topics. Previous articles in this series can be found here and also here. The theorem discussed here is the central limit theorem.

In the Google paper, the authors enumerate many risk factors, design patterns, and anti-patterns to needs to be taken into consideration in an architecture. These include design patterns such as: boundary erosion, entanglement, hidden feedback loops, undeclared consumers, data dependencies and changes in the external world. By contrast, Deep Learning systems (applies equally to machine learning), code is created from training data. A recent paper from the folks at Berkeley are exploring the requirements for building these new kinds of systems (see: "Real-Time Machine Learning: The Missing Pieces").

The future of work looks full of promise. Combining human brainpower with artificial intelligence, virtual reality and automatization will revolutionize how we work. "The future of work looks full of promise." Already, robotic enhancement is helping humans exceed their natural capabilities. AI is opening the door to real-time, personalized intelligent services, cutting waste and maximizing results.

Scala and Spark for Big Data and Machine Learning by Jose Portilla will teach you how to use Scala & Apache Spark. You will understand how to work with Big Data and Machine Learning. Apache Spark 2.0 with Scala – Hands On with Big Data! by Frank Kane will teach you how to work with Big data using Scala & Apache Spark. You will see and work through 20 hands-on examples of analyzing large data sets. Taming Big Data with Spark Streaming and Scala – Hands On! by Frank Kane will teach you how to create Spark applications using Scala programming.

We consider the optimal value of information (VoI) problem, where the goal is to sequentially select a set of tests with a minimal cost, so that one can efficiently make the best decision based on the observed outcomes. Existing algorithms are either heuristics with no guarantees, or scale poorly (with exponential run time in terms of the number of available tests). Moreover, these methods assume a known distribution over the test outcomes, which is often not the case in practice. We propose an efficient sampling-based online learning framework to address the above issues. First, assuming the distribution over hypotheses is known, we propose a dynamic hypothesis enumeration strategy, which allows efficient information gathering with strong theoretical guarantees. We show that with sufficient amount of samples, one can identify a near-optimal decision with high probability. Second, when the parameters of the hypotheses distribution are unknown, we propose an algorithm which learns the parameters progressively via posterior sampling in an online fashion. We further establish a rigorous bound on the expected regret. We demonstrate the effectiveness of our approach on a real-world interactive troubleshooting application and show that one can efficiently make high-quality decisions with low cost.

An electric glove which can convert sign language into text messages has been unveiled by scientists. The $100 (£77) device will will allow deaf people to instantly send messages to those who don't understand sign language, according to its inventors. Researchers fitted a standard sports glove with nine flexible strain sensors which react when a user bends their fingers to create the new device. The device consists of a sports glove which has been fitted with nine stretchable sensors positioned over the knuckles. When a user bends their fingers or thumb to sign a letter, the sensors stretch, which causes an electrical signal to be produced.

The team at Alphabet have used a reinforced learning program to teach the DeepMind AI how to do parkour. Reinforced learning (RL) is a common tool for teaching and guiding behavior by using a reward system. Basically good or desirable behavior gets rewards and undesirable behavior gets nothing. The aim of the project was to investigate if simple rewards systems would also work in complex environments. A virtual parkour course was designed with steps, ledges, hurdles, and drops.