A group of scientists from the Massachusetts Institute of Technology (United States) has created a machine learning system that processes sounds like people. This model can understand the meaning of a word and classify a song according to its genre or style: classical, jazz, pop, rock, blues, soul, hip hop, techno, house, etc. It is the first invention of this type that mimics the way the brain works. As the experiments carried out at MIT show, it can compete in precision with humans. The research, published in the journal Neuron, is based on deep neural networks, that is, a structure inspired by brain cells that analyses information by layers.

If it's the SC18 supercomputing conference, then there must be lists. The twice-yearly show is most famous for the Top500 list of the world's fastest supercomputers that use the Linpack parallel Fortan benchmark, a list that helps the industry gauge progress in performance, the growing influence of new technologies like GPU accelerators from Nvidia and AMD and the rise of new architectures, as marked this year by the introduction of the first supercomputer on the list powered by Arm-based processors. The "Astra" supercomputer, built by Hewlett Packard Enterprise and deployed at the Sandia National Laboratories, runs on 125,328 Cavium ThunderX2 cores and now sits in the number 205 slot. The list also helps fuel the ongoing global competition for supercomputer supremacy, with the United States this year finally retaking the top spot from China's Sunway TaihuLight in July with the Summit system based on IBM Power9 and Nvidia Volta compute engines, and then Sierra, a similarly architected machine, taking the number-two slot at this week's SC18 show in Dallas, pushing TaihuLight to number-three. However, China now claims 227 systems – or about 45 percent of the total number – on the Top500 list, with the United States dropping to an all-time low of 109, or 22 percent. The Green500 ranks supercomputers based on power efficiency.

In a hilarious turn of events last month, a Russian robot named Boris was unmasked as a man in a robot suit. Likewise, state-run media in China unveiled its AI reporter in November, and to this day it's not clear if this is an actual AI system boiling down news stories or just a synthesized voice with an avatar. More fabricated robotic theatrics appeared to be on display this week at the Consumer Electronics Show in Las Vegas, where LG CTO I.P. Park delivered the opening CES keynote address. Park was accompanied onstage for the hour-long presentation by CLOi, a conceptual robot line perhaps best known for failing during a live demo at CES a year ago. This year, however, CLOi did a bit of everything: The robot acted as co-host, cracked jokes, delivered some LG HomeBrew beer, and even helped some guy who hates blind dates find true love.

ABSTRACT: Most of mathematic forgetting curve models fit well with the forgetting data under the learning condition of one time rather than repeated. In the paper, a convolution model of forgetting curve is proposed to simulate the memory process during learning. In this model, the memory ability (i.e. the central procedure in the working memory model) and learning material (i.e. the input in the working memory model) is regarded as the system function and the input function, respectively. The status of forgetting (i.e. the output in the working memory model) is regarded as output function or the convolution result of the memory ability and learning material. The model is applied to simulate the forgetting curves in different situations. The results show that the model is able to simulate the forgetting curves not only in one time learning condition but also in multi-times condition. The model is further verified in the experiments of Mandarin tone learning for Japanese learners. And the predicted curve fits well on the test points. Keywords: Memory forgetting curves; Convolution; Mathematical modeling 1.Introduction Since Ebbinghaus proposed the eminent'forgetting curve' to quantitatively describe the procedure of memory [1], researchers have made great effort to find out the exactly form of the models for forgetting curve. The problem is still being considered as'central theoretical importance' [2].

We address the problem of designing a conversational avatar capable of a sequence of casual conversations with older adults. Users at risk of loneliness, social anxiety or a sense of ennui may benefit from practicing such conversations in private, at their convenience. We describe an automatic spoken dialogue manager for LISSA, an on-screen virtual agent that can keep older users involved in conversations over several sessions, each lasting 10-20 minutes. The idea behind LISSA is to improve users' communication skills by providing feedback on their non-verbal behavior at certain points in the course of the conversations. In this paper, we analyze the dialogues collected from the first session between LISSA and each of 8 participants. We examine the quality of the conversations by comparing the transcripts with those collected in a WOZ setting. LISSA's contributions to the conversations were judged by research assistants who rated the extent to which the contributions were "natural", "on track", "encouraging", "understanding", "relevant", and "polite". The results show that the automatic dialogue manager was able to handle conversation with the users smoothly and naturally.

A crucial challenge in image-based modeling of biomedical data is to identify trends and features that separate normality and pathology. In many cases, the morphology of the imaged object exhibits continuous change as it deviates from normality, and thus a generative model can be trained to model this morphological continuum. Moreover, given side information that correlates to certain trend in morphological change, a latent variable model can be regularized such that its latent representation reflects this side information. In this work, we use the Wasserstein Auto-encoder to model this pathology continuum, and apply the Hilbert-Schmitt Independence Criterion (HSIC) to enforce dependency between certain latent features and the provided side information. We experimentally show that the model can provide disentangled and interpretable latent representations and also generate a continuum of morphological changes that corresponds to change in the side information.

In this paper we focus on the problem of finding the optimal weights of the shallowest of neural networks consisting of a single Rectified Linear Unit (ReLU). These functions are of the form $\mathbf{x}\rightarrow \max(0,\langle\mathbf{w},\mathbf{x}\rangle)$ with $\mathbf{w}\in\mathbb{R}^d$ denoting the weight vector. We focus on a planted model where the inputs are chosen i.i.d. from a Gaussian distribution and the labels are generated according to a planted weight vector. We first show that mini-batch stochastic gradient descent when suitably initialized, converges at a geometric rate to the planted model with a number of samples that is optimal up to numerical constants. Next we focus on a parallel implementation where in each iteration the mini-batch gradient is calculated in a distributed manner across multiple processors and then broadcast to a master or all other processors. To reduce the communication cost in this setting we utilize a Quanitzed Stochastic Gradient Scheme (QSGD) where the partial gradients are quantized. Perhaps unexpectedly, we show that QSGD maintains the fast convergence of SGD to a globally optimal model while significantly reducing the communication cost. We further corroborate our numerical findings via various experiments including distributed implementations over Amazon EC2.

Semantic segmentation remains a computationally intensive algorithm for embedded deployment even with the rapid growth of computation power. Thus efficient network design is a critical aspect especially for applications like automated driving which requires real-time performance. Recently, there has been a lot of research on designing efficient encoders that are mostly task agnostic. Unlike image classification and bounding box object detection tasks, decoders are computationally expensive as well for semantic segmentation task. In this work, we focus on efficient design of the segmentation decoder and assume that an efficient encoder is already designed to provide shared features for a multi-task learning system. We design a novel efficient non-bottleneck layer and a family of decoders which fit into a small run-time budget using VGG10 as efficient encoder. We demonstrate in our dataset that experimentation with various design choices led to an improvement of 10\% from a baseline performance.

The area of Handwritten Signature Verification has been broadly researched in the last decades, but remains an open research problem. In offline (static) signature verification, the dynamic information of the signature writing process is lost, and it is difficult to design good feature extractors that can distinguish genuine signatures and skilled forgeries. This verification task is even harder in writer independent scenarios which is undeniably fiscal for realistic cases. In this paper, we have proposed an Ensemble model for offline writer, independent signature verification task with Deep learning. We have used two CNNs for feature extraction, after that RGBT for classification & Stacking to generate final prediction vector. We have done extensive experiments on various datasets from various sources to maintain a variance in the dataset. We have achieved the state of the art performance on various datasets.

Early recognition of abnormal rhythm in ECG signals is crucial for monitoring or diagnosing patients' cardiac conditions and increasing the success rate of the treatment. Classifying abnormal rhythms into fine-grained categories is very challenging due to the the broad taxonomy of rhythms, noises and lack of real-world data and annotations from large number of patients. This paper presents a new ECG classification method based on Deep Convolutional Neural Networks (DCNN) and online decision fusion. Different from previous methods which utilize hand-crafted features or learn features from the original signal domain, the proposed DCNN based method learns features and classifiers from the time-frequency domain in an end-to-end manner. First, the ECG wave signal is transformed to time-frequency domain by using Short-Time Fourier Transform. Next, specific DCNN models are trained on ECG samples of specific length. Finally, an online decision fusion method is proposed to fuse past and current decisions from different models into a more accurate one. Experimental results on both synthetic and real-world ECG datasets convince the effectiveness and efficiency of the proposed method.