What could potentially be the use of doing that? These are just some of the questions you must have had when you read the title of this article. And it's only fair – I had the exact same thoughts when I first came across this concept! The time series data most of us are exposed to deals primarily with generating forecasts. Whether that's predicting the demand or sales of a product, the count of passengers in an airline or the closing price of a particular stock, we are used to leveraging tried and tested time series techniques for forecasting requirements.

Artificial intelligence (AI) is in the midst of an undeniable surge in popularity, and enterprises are becoming particularly interested in a form of AI known as deep learning. According to Gartner, AI will likely generate $1.2 trillion in business value for enterprises in 2018, 70 percent more than last year. "AI promises to be the most disruptive class of technologies during the next 10 years due to advances in computational power, volume, velocity and variety of data, as well as advances in deep neural networks (DNNs)," said John-David Lovelock, research vice president at Gartner.

We present a novel technique for assessing the dynamics of multiphase fluid flow in the oil reservoir. We demonstrate an efficient workflow for handling the 3D reservoir simulation data in a way which is orders of magnitude faster than the conventional routine. The workflow (we call it "Metamodel") is based on a projection of the system dynamics into a latent variable space, using Variational Autoencoder model, where Recurrent Neural Network predicts the dynamics. We show that being trained on multiple results of the conventional reservoir modelling, the Metamodel does not compromise the accuracy of the reservoir dynamics reconstruction in a significant way. It allows forecasting not only the flow rates from the wells, but also the dynamics of pressure and fluid saturations within the reservoir. The results open a new perspective in the optimization of oilfield development as the scenario screening could be accelerated sufficiently.

The scientific and technological revolution of the Internet of Things has begun in the area of oceanography. Historically, humans have observed the ocean from an external viewpoint in order to study it. In recent years, however, changes have occurred in the ocean, and laboratories have been built on the seafloor. Approximately 70.8% of the Earth's surface is covered by oceans and rivers. The Ocean of Things is expected to be important for disaster prevention, ocean-resource exploration, and underwater environmental monitoring. Unlike traditional wireless sensor networks, the Ocean Network has its own unique features, such as low reliability and narrow bandwidth. These features will be great challenges for the Ocean Network. Furthermore, the integration of the Ocean Network with artificial intelligence has become a topic of increasing interest for oceanology researchers. The Cognitive Ocean Network (CONet) will become the mainstream of future ocean science and engineering developments. In this article, we define the CONet. The contributions of the paper are as follows: (1) a CONet architecture is proposed and described in detail; (2) important and useful demonstration applications of the CONet are proposed; and (3) future trends in CONet research are presented.

A major obstacle for widespread deployment of frequency division duplex (FDD)-based Massive multiple-input multipleoutput (MIMO)communications is the large signaling overhead for reporting full downlink (DL) channel state information (CSI) back to the basestation (BS), in order to enable closed-loop precoding. We completely remove this overhead by a deep-learning based channel extrapolation (or "prediction") approach and demonstrate that a neural network (NN) at the BS can infer the DL CSI centered around a frequency f UL; nomore pilot/reporting overhead is needed than with a genuine time division duplex (TDD)-based system. The rationale is that scatterers and the large-scale propagation environment are sufficiently similar to allow a NN to learn about the physical connections and constraints between two neighboring frequency bands, and thus provide a well-operating system even when classic extrapolation methods, like the Wiener filter (used as a baseline for comparison throughout) fails. We study its performance for various state-of-the-art Massive MIMO channel models, and, even more so, evaluate the scheme using actual Massive MIMO channel measurements, rendering it to be practically feasible at negligible loss in spectral efficiency when compared to a genuine TDD-based system. I. INTRODUCTION With a significant increase in area throughput, Massive multiple-input multiple-output (MIMO) antenna communication has become an enabling technology for the upcoming fifth generation (5G) wireless mobile communication systems [1], [2], [3], [4]. However, Massive MIMO systems described in current research literature commonly exploit channel reciprocity and hence rely on time division duplex (TDD)-based approaches [1], i.e., uplink (UL) and downlink (DL) channels share the same frequency band in orthogonal time intervals. Achieving such reciprocity in practice requires accurate hardware with costly calibration circuitry. To mitigate this issue, various alternatives to a full Massive MIMO system have been proposed such as the grid of beams [5] and codebook Massive MIMO [6].

Traditional photo-id involves a laborious manual process of matching each dolphin fin photograph captured in the field to a catalogue of known individuals. Weexamine this problem in the context of open-set recognition andutilise a triplet loss function to learn a compact representation of fin images in a Euclidean embedding, where the Euclidean distance metric represents fin similarity. We show that this compact representation can be successfully learnt from a fairly small (in deep learning context) training set and still generalise well to out-of-sample identities (completely new dolphin individuals), with top-1 and top-5 test set (37 individuals) accuracy of 90.5 2 and 93.6 1 percent. In the presence of 1200 distractors, top-1 accuracy dropped by 12%; however, top-5 accuracy saw only a 2.8% drop. I. INTRODUCTION Dolphin photo-identification (photo-ID) studies involve photographing dolphindorsal fins during field work and then having a human categorise images into unique individual animals andmatching them with an existing catalogue of known individuals. Individuals are identified by natural features that can be observed on the fins--these features vary between species, but typically include the pattern of nicks and notches on the trailing edge of the fin, the scratches/rake marks/scars on the fin and (for some species) the pigmentation patterns [1]. Matchingof new images from the field against a large catalogue is time consuming, because it requires a human to compare each candidate image to every fin in the catalogue, taking O(mn) average time (where m is the number of new images and n is the number of catalogued individuals). Moreover, as n increases over time as more individuals are added to the catalogue, so does the likelihood of making a mistake, putting catalogue integrity at risk.

Majority of semantic segmentation algorithms operate on a single frame even in the case of videos. In this work, the goal is to exploit temporal information within the algorithm model for leveraging motion cues and temporal consistency. We propose two simple high-level architectures based on Recurrent FCN (RFCN) and Multi-Stream FCN (MSFCN) networks. In case of RFCN, a recurrent network namely LSTM is inserted between the encoder and decoder. MSFCN combines the encoders of different frames into a fused encoder via 1x1 channel-wise convolution. We use a ResNet50 network as the baseline encoder and construct three networks namely MSFCN of order 2 & 3 and RFCN of order 2. MSFCN-3 produces the best results with an accuracy improvement of 9% and 15% for Highway and New York-like city scenarios in the SYNTHIA-CVPR'16 dataset using mean IoU metric. MSFCN-3 also produced 11% and 6% for SegTrack V2 and DAVIS datasets over the baseline FCN network. We also designed an efficient version of MSFCN-2 and RFCN-2 using weight sharing among the two encoders. The efficient MSFCN-2 provided an improvement of 11% and 5% for KITTI and SYNTHIA with negligible increase in computational complexity compared to the baseline version.

Abstract--In this paper, a spintronic neuromorphic reconfigurable Array(SNRA) is developed to fuse together power-efficient probabilistic and infield programmable deterministic computing during both training and evaluation phases of restricted Boltzmann machines(RBMs). First, probabilistic spin logic devices are used to develop an RBM realization which is adapted to construct deep belief networks (DBNs) having one to three hidden layers of size 10 to 800 neurons each. The functionality of our proposed CD hardware implementation is validated using ModelSim simulations. We synthesize the developed Verilog HDL implementation of our proposed test/train control circuitry for various DBN topologies where the maximal RBM dimensions yield resource utilization ranging from 51 to 2,421 lookup tables (LUTs). Next, we leverage spin Hall effect (SHE)-magnetic tunnel junction (MTJ) based nonvolatile LUTs circuits as an alternative for static random access memory (SRAM)-based LUTs storing the deterministic logic configuration to form a reconfigurable fabric. Finally, we compare the performance of our proposed SNRA with SRAMbased configurablefabrics focusing on the area and power consumption induced by the LUTs used to implement both CD and evaluation modes. The results obtained indicate more than 80% reduction in combined dynamic and static power dissipation, while achieving at least 50% reduction in device count.

This paper develops the FastRNN and FastGRNN algorithms to address the twin RNN limitations of inaccurate training and inefficient prediction. Previous approaches have improved accuracy at the expense of prediction costs making them infeasible for resource-constrained and real-time applications. Unitary RNNs have increased accuracy somewhat by restricting the range of the state transition matrix's singular values but have also increased the model size as they require a larger number of hidden units to make up for the loss in expressive power. Gated RNNs have obtained state-of-the-art accuracies by adding extra parameters thereby resulting in even larger models. FastRNN addresses these limitations by adding a residual connection that does not constrain the range of the singular values explicitly and has only two extra scalar parameters. FastGRNN then extends the residual connection to a gate by reusing the RNN matrices to match state-of-the-art gated RNN accuracies but with a 2-4x smaller model. Enforcing FastGRNN's matrices to be low-rank, sparse and quantized resulted in accurate models that could be up to 35x smaller than leading gated and unitary RNNs. This allowed FastGRNN to accurately recognize the "Hey Cortana" wakeword with a 1 KB model and to be deployed on severely resource-constrained IoT microcontrollers too tiny to store other RNN models. FastGRNN's code is available at https://github.com/Microsoft/EdgeML/.

Estimating the relative importance of each sample in a training set has important practical and theoretical value, such as in importance sampling or curriculum learning. This kind of focus on individual samples invokes the concept of sample-wise learnability: How easy is it to correctly learn each sample (cf. PAC learnability)? In this paper, we approach the sample-wise learnability problem within a deep learning context. We propose a measure of the learnability of a sample with a given deep neural network (DNN) model. The basic idea is to train the given model on the training set, and for each sample, aggregate the hits and misses over the entire training epochs. Our experiments show that the sample-wise learnability measure collected this way is highly linearly correlated across different DNN models (ResNet-20, VGG-16, and MobileNet), suggesting that such a measure can provide deep general insights on the data's properties. We expect our method to help develop better curricula for training, and help us better understand the data itself.