While significant attention has been recently focused on designing supervised deep semantic segmentation algorithms for vision tasks, there are many domains in which sufficient supervised pixel-level labels are difficult to obtain. In this paper, we revisit the problem of purely unsupervised image segmentation and propose a novel deep architecture for this problem. We borrow recent ideas from supervised semantic segmentation methods, in particular by concatenating two fully convolutional networks together into an autoencoder--one for encoding and one for decoding. The encoding layer produces a k-way pixelwise prediction, and both the reconstruction error of the autoencoder as well as the normalized cut produced by the encoder are jointly minimized during training. When combined with suitable postprocessing involving conditional random field smoothing and hierarchical segmentation, our resulting algorithm achieves impressive results on the benchmark Berkeley Segmentation Data Set, outperforming a number of competing methods.

Since the launch of Google Glass in 2014, smart glasses have mainly been designed to support micro-interactions. The ultimate goal for them to become an augmented reality interface has not yet been attained due to an encumbrance of controls. Augmented reality involves superimposing interactive computer graphics images onto physical objects in the real world. This survey reviews current research issues in the area of human computer interaction for smart glasses. The survey first studies the smart glasses available in the market and afterwards investigates the interaction methods proposed in the wide body of literature. The interaction methods can be classified into hand-held, touch, and touchless input. This paper mainly focuses on the touch and touchless input. Touch input can be further divided into on-device and on-body, while touchless input can be classified into hands-free and freehand. Next, we summarize the existing research efforts and trends, in which touch and touchless input are evaluated by a total of eight interaction goals. Finally, we discuss several key design challenges and the possibility of multi-modal input for smart glasses.

There is an increasing need to bring machine learning to a wide diversity of hardware devices. Current frameworks rely on vendor-specific operator libraries and optimize for a narrow range of server-class GPUs. Deploying workloads to new platforms -- such as mobile phones, embedded devices, and accelerators (e.g., FPGAs, ASICs) -- requires significant manual effort. We propose TVM, a compiler that exposes graph-level and operator-level optimizations to provide performance portability to deep learning workloads across diverse hardware back-ends. TVM solves optimization challenges specific to deep learning, such as high-level operator fusion, mapping to arbitrary hardware primitives, and memory latency hiding. It also automates optimization of low-level programs to hardware characteristics by employing a novel, learning-based cost modeling method for rapid exploration of code optimizations. Experimental results show that TVM delivers performance across hardware back-ends that are competitive with state-of-the-art, hand-tuned libraries for low-power CPU, mobile GPU, and server-class GPUs. We also demonstrate TVM's ability to target new accelerator back-ends, such as the FPGA-based generic deep learning accelerator. The system is open sourced and in production use inside several major companies.

{p=The lack of global data flow in healthcare systems negatively impacts decision-making both locally and globally. This Chapter aims to introduce global health specialists to causal loop diagrams (CLDs) and system dynamics models to help them better frame, examine, and understand complex issues characteristic to data-rich ecosystems. As machine and statistical learning tools become popular among data scientists and researchers, they can help us understand how various data sources and variables interact with each other mechanistically. These complementary approaches go a step beyond machine and statistical learning tools to represent causality between variables affecting data-driven ecosystems and decision-making., h1=Abstract}

The graph convolutional networks (GCN) recently proposed by Kipf and Welling are an effective graph model for semi-supervised learning. This model, however, was originally designed to be learned with the presence of both training and test data. Moreover, the recursive neighborhood expansion across layers poses time and memory challenges for training with large, dense graphs. To relax the requirement of simultaneous availability of test data, we interpret graph convolutions as integral transforms of embedding functions under probability measures. Such an interpretation allows for the use of Monte Carlo approaches to consistently estimate the integrals, which in turn leads to a batched training scheme as we propose in this work---FastGCN. Enhanced with importance sampling, FastGCN not only is efficient for training but also generalizes well for inference. We show a comprehensive set of experiments to demonstrate its effectiveness compared with GCN and related models. In particular, training is orders of magnitude more efficient while predictions remain comparably accurate.

This paper improves state-of-the-art visual object trackers that use online adaptation. Our core contribution is an offline meta-learning-based method to adjust the initial deep networks used in online adaptation-based tracking. The meta learning is driven by the goal of deep networks that can quickly be adapted to robustly model a particular target in future frames. Ideally the resulting models focus on features that are useful for future frames, and avoid overfitting to background clutter, small parts of the target, or noise. By enforcing a small number of update iterations during meta-learning, the resulting networks train significantly faster. We demonstrate this approach on top of the high performance tracking approaches: tracking-by-detection based MDNet and the correlation based CREST. Experimental results on standard benchmarks, OTB2015 and VOT2016, show that our meta-learned versions of both trackers improve speed, accuracy, and robustness.

This article has to do with the derivation and solution of the Fokker--Planck equation associated to the momentum-independent Wigner function, of a particle subjected to a harmonic external field and immersed in a ohmic thermal bath of quantum harmonic oscillators. The strategy employed is a simplified version of the phenomenological approach of Schramm, Jung and Grabert of interpreting the operators as c-numbers to derive the adjoint equation arising from a twofold transformation of the Wigner function of the entire phase space. The statistical properties of the random noise comes from the integral functional theory of Grabert, Schramm and Ingold. By means of a single Wigner transformation, it is found a simpler master quantum equation than that of mentioned before. The Wigner function reproduces the known results of the classical limit. This allowed to rewrite the underdamped classical Langevin equation as a first order stochastic differential equation with time-dependent drift and diffusion terms.