The concept of stochastic configuration networks (SCNs) others a solid framework for fast implementation of feedforward neural networks through randomized learning. Unlike conventional randomized approaches, SCNs provide an avenue to select appropriate scope of random parameters to ensure the universal approximation property. In this paper, a deep version of stochastic configuration networks, namely deep stacked stochastic configuration network (DSSCN), is proposed for modeling non-stationary data streams. As an extension of evolving stochastic connfiguration networks (eSCNs), this work contributes a way to grow and shrink the structure of deep stochastic configuration networks autonomously from data streams. The performance of DSSCN is evaluated by six benchmark datasets. Simulation results, compared with prominent data stream algorithms, show that the proposed method is capable of achieving comparable accuracy and evolving compact and parsimonious deep stacked network architecture.

With ever-increasing computational demand for deep learning, it is critical to investigate the implications of the numeric representation and precision of DNN model weights and activations on computational efficiency. In this work, we explore unconventional narrow-precision floating-point representations as it relates to inference accuracy and efficiency to steer the improved design of future DNN platforms. We show that inference using these custom numeric representations on production-grade DNNs, including GoogLeNet and VGG, achieves an average speedup of 7.6x with less than 1% degradation in inference accuracy relative to a state-of-the-art baseline platform representing the most sophisticated hardware using single-precision floating point. To facilitate the use of such customized precision, we also present a novel technique that drastically reduces the time required to derive the optimal precision configuration.

Abstract-- This paper addresses the complete area coverage problem of a known environment by multiple-robots. Complete area coverage is the problem of moving an end-effector over all available space while avoiding existing obstacles. In such tasks, using multiple robots can increase the efficiency of the area coverage in terms of minimizing the operational time and increase the robustness in the face of robot attrition. Unfortunately, the problem of finding an optimal solution for such an area coverage problem with multiple robots is known to be NPcomplete. The first solution presented is a direct extension of an efficient single robot area coverage algorithm, based on an exact cellular decomposition. The second algorithm is a greedy approach that divides the area into equal regions and applies an efficient single-robot coverage algorithm to each region. Results indicate that our approaches provide good coverage distribution between robots and minimize the workload per robot, meanwhile ensuring complete coverage of the area. Index Terms-- Multiple and distributed robots, path planning, coverage.

Abstract-- Driving is a social activity: drivers often indicate their intent to change lanes via motion cues. We consider mixed-autonomy traffic where a Human-driven V ehicle (HV) and an Autonomous V ehicle (A V) drive together . We propose a planning framework where the degree to which the A V considers the other agent's reward is controlled by a selfishness factor . We test our approach on a simulated two-lane highway where the A V and HV merge into each other's lanes. In a user study with 21 subjects and 6 different selfishness factors, we found that our planning approach was sound and that both agents had less merging times when a factor that balances the rewards for the two agents was chosen. Our results on double lane merging suggest it to be a nonzero-sum game and encourage further investigation on collaborative decision making algorithms for mixed-autonomy traffic. Driving is a social activity: drivers indicate their willingness to change lanes by subtle cues such as eye contact, or by not-so-subtle cues such as adjusting their speed and position [1]. There has been impressive demonstrations of Autonomous V ehicle (A V) technology [2]-[4], however one of the remaining challenges in this area is reading those cues to estimate the intentions of other agents as well as using cues to communicate the intentions of the A V . As A Vs become commonplace, the situations where A V's and Human-driven V ehicles (HV) interact will increase.

We contribute the first large-scale dataset of scene sketches, SketchyScene, with the goal of advancing research on sketch understanding at both the object and scene level. The dataset is created through a novel and carefully designed crowdsourcing pipeline, enabling users to efficiently generate large quantities of realistic and diverse scene sketches. SketchyScene contains more than 29,000 scene-level sketches, 7,000+ pairs of scene templates and photos, and 11,000+ object sketches. All objects in the scene sketches have ground-truth semantic and instance masks. The dataset is also highly scalable and extensible, easily allowing augmenting and/or changing scene composition. We demonstrate the potential impact of SketchyScene by training new computational models for semantic segmentation of scene sketches and showing how the new dataset enables several applications including image retrieval, sketch colorization, editing, and captioning, etc. The dataset and code can be found at https://github.com/SketchyScene/SketchyScene.

We study instancewise feature importance scoring as a method for model interpretation. Any such method yields, for each predicted instance, a vector of importance scores associated with the feature vector. Methods based on the Shapley score have been proposed as a fair way of computing feature attributions of this kind, but incur an exponential complexity in the number of features. This combinatorial explosion arises from the definition of the Shapley value and prevents these methods from being scalable to large data sets and complex models. We focus on settings in which the data have a graph structure, and the contribution of features to the target variable is well-approximated by a graph-structured factorization. In such settings, we develop two algorithms with linear complexity for instancewise feature importance scoring. We establish the relationship of our methods to the Shapley value and another closely related concept known as the Myerson value from cooperative game theory. We demonstrate on both language and image data that our algorithms compare favorably with other methods for model interpretation.

Multi-output Gaussian processes (MOGPs) are recently extended by using spectral mixture kernel, which enables expressively pattern extrapolation with a strong interpretation. In particular, Multi-Output Spectral Mixture kernel (MOSM) is a recent, powerful state of the art method. However, MOSM cannot reduce to the ordinary spectral mixture kernel (SM) when using a single channel. Moreover, when the spectral density of different channels is either very close or very far from each other in the frequency domain, MOSM generates unreasonable scale effects on cross weights which produces an incorrect description of the channel correlation structure. In this paper, we tackle these drawbacks and introduce a principled multi-output convolution spectral mixture kernel (MOCSM) framework. In our framework, we model channel dependencies through convolution of time and phase delayed spectral mixtures between different channels.

Masayoshi Son, the founder of tech giant SoftBank and the richest man in Japan, says he is devoting 97% of his "time and brain" to the scientific field of artificial intelligence. Son made his comments on Monday as SoftBank reported a 49% jump in profits, according to The Financial Times. The profit rise was largely driven by a strong performance from SoftBank's $100 billion Vision Fund. Backed by Saudi Arabia's Sovereign Wealth Fund and companies like Apple, the Vision Fund is the largest tech fund in the world. SoftBank has used the Vision Fund, which is run out of an office in London's Mayfair, to invest in a wide range of companies spanning agriculture, transport, satellites, payments, computer chips, and ecommerce.

In late May, Chinese facial recognition technology developer SenseTime Group announced it had raised $620 million in a second round of funding. The raise valued the company over $4.5 billion, making it the world's most valuable AI unicorn. SenseTime reportedly became profitable last year. Meanwhile, UiPath--an enterprise robotic process automation (RPA) software company--brought in $153 million in a massive Series B round led by previous investor Accel. UiPath said the round pushed it into unicorn status and followed a record year of growth.

DJI apparently felt that its tiny Spark drone wasn't quite cute enough. The company has unveiled a version of the Spark that slaps Line Friends' extra-adorable Brown the bear on its back. DJI believes the drone is becoming a "lifestyle accessory" -- it's something you might always carry with you, so you might as well have a quadcopter that echoes your style. We'd question that philosophy when you can't see Brown the moment you start using the drone, but it does beat the simple colored shells that usually pass for fashion in the drone world. Apart from the ursine appearance, this is the same as the Spark you've come to know.