Decentralized machine learning is a promising emerging paradigm in view of global challenges of data ownership and privacy. We consider learning of linear classification and regression models, in the setting where the training data is decentralized over many user devices, and the learning algorithm must run on-device, on an arbitrary communication network, without a central coordinator. We propose COLA, a new decentralized training algorithm with strong theoretical guarantees and superior practical performance. Our framework overcomes many limitations of existing methods, and achieves communication efficiency, scalability, elasticity as well as resilience to changes in data and participating devices.

Tuning cellular network performance against always occurring wireless impairments can dramatically improve reliability to end users. In this paper, we formulate cellular network performance tuning as a reinforcement learning (RL) problem and provide a solution to improve the signal to interferenceplus-noise ratio (SINR) for indoor and outdoor environments. By leveraging the ability of Q-learning to estimate future SINR improvement rewards, we propose two algorithms: (1) voice over LTE (VoLTE) downlink closed loop power control (PC) and (2) self-organizing network (SON) fault management. The VoLTE PC algorithm uses RL to adjust the indoor base station transmit power so that the effective SINR meets the target SINR. The SON fault management algorithm uses RL to improve the performance of an outdoor cluster by resolving faults in the network through configuration management. Both algorithms exploit measurements from the connected users, wireless impairments, and relevant configuration parameters to solve a non-convex SINR optimization problem using RL. Simulation results show that our proposed RL based algorithms outperform the industry standards today in realistic cellular communication environments. The tuning of network performance aims at providing the end user with excellent quality of experience (QoE). With over 1.5 billion smartphones used globally, demand patterns have The authors are with the Wireless Networking and Communications Group, Department of Electrical and Computer Engineering, The University of Texas at Austin, Austin, TX, 78712, USA email: {faris.mismar, This paper is an expanded journal version of [1] and [2]. 2 Demands have shifted towards reliable packetized voice and applications with higher data rates and lower latencies [4].

A number of recent machine learning papers work with an automated style transfer for texts and, counter to intuition, demonstrate that there is no consensus formulation of this NLP task. Different researchers propose different algorithms, datasets and target metrics to address it. This short opinion paper aims to discuss possible formalization of this NLP task in anticipation of a further growing interest to it.

Deep neural networks are the state-of-the-art methods for many real-world tasks, such as computer vision, natural language processing and speech recognition. For all its popularity, deep neural networks are also criticized for consuming a lot of memory and draining battery life of devices during training and inference. This makes it hard to deploy these models on mobile or embedded devices which have tight resource constraints. Quantization is recognized as one of the most effective approaches to satisfy the extreme memory requirements that deep neural network models demand. Instead of adopting 32-bit floating point format to represent weights, quantized representations store weights using more compact formats such as integers or even binary numbers. Despite a possible degradation in predictive performance, quantization provides a potential solution to greatly reduce the model size and the energy consumption. In this survey, we give a thorough review of different aspects of quantized neural networks. Current challenges and trends of quantized neural networks are also discussed.

Machine learning (ML) techniques such as (deep) artificial neural networks (DNN) are solving very successfully a plethora of tasks and provide new predictive models for complex physical, chemical, biological and social systems. However, in most cases this comes with the disadvantage of acting as a black box, rarely providing information about what made them arrive at a particular prediction. This black box aspect of ML techniques can be problematic especially in medical diagnoses, so far hampering a clinical acceptance. The present paper studies the uniqueness of individual gait patterns in clinical biomechanics using DNNs. By attributing portions of the model predictions back to the input variables (ground reaction forces and full-body joint angles), the Layer-Wise Relevance Propagation (LRP) technique reliably demonstrates which variables at what time windows of the gait cycle are most relevant for the characterisation of gait patterns from a certain individual. By measuring the timeresolved contribution of each input variable to the prediction of ML techniques such as DNNs, our method describes the first general framework that enables to understand and interpret non-linear ML methods in (biomechanical) gait analysis and thereby supplies a powerful tool for analysis, diagnosis and treatment of human gait.

Abstract--Hashing techniques have been applied broadly in large-scale retrieval tasks due to their low storage requirements and high speed of processing. Many hashing methods have shown promising performance but as they fail to exploit all structural information in learning the hashing function, they leave a scope for improvement. The paper proposes a novel discrete hashing learning framework which jointly performs classifier learning and subspace learning for cross-modal retrieval. Concretely, the framework proposed in the paper includes two stages, namely a kernelization process and a quantization process. The aim of kernelization is to learn a common subspace where heterogeneous data can be fused. The quantization process is designed to learn discriminative unified hashing codes. Extensive experiments on three publicly available datasets clearly indicate the superiority of our method compared with the state-of-the-art methods.

Nurse Florence Nightingale may be most well-known as the British Army's lady with the lamp, assiduously conducting night rounds and attending to the wounded by candle light. But by demonstrating the link between poor sanitary conditions and high mortality rates in hospitals, it was her pioneering use of data collection and visualisation that still resonates today. In 2018, medicine faces a different set of challenges, with longer life expectancies and population growth increasing the number of patients suffering with chronic conditions requiring ongoing care. This has led to the cost of delivering health care increasing faster than GDP and quickly becoming unsustainable. Over 160 years might have passed since Florence Nightingale's day, but addressing these challenges still depends on data.

Over 200 attendees attended the blockchain meetup in Istanbul, Turkey co-organized by SamuraiSignals and MATRIX AI Network on July 28th, to explore leading edge developments in blockchain. In his talk, IDA cofounder, Mr. Walter Wang outlined four innovations shaping the future of asset digitization. Wang said that the technical basis for asset digitization, is creating a digitized representation of real assets or IP assets in a binary code format -- however, there are currently the following challenges to overcome before the technology can be applied widely. There is an asymmetry in transparency of asset information. How to extend legal protections to digital assets?

Machine learning will make banking easier before it makes it better, say German fintechs and banks. Customers might not yet notice it, but Germany's banks are slowly waking up to artificial intelligence. They hope thinking computers can help them sort through regulatory jungles, fight money laundering or even help analyze customers. "In the next few years, the increase is likely to be driven mainly by efficiency improvements, and later new products and services could have a greater effect," says Christian Kirschniak, a data expert and partner at PwC. The consultancy believes AI's contribution could be similar to that of the first computer revolution and contribute $2 trillion (€1.73 trillion) to global GDP by 2030, in part by relieving financial sector employees of tedious, monotonous tasks that traditional computers can't perform.

Deep learning models have achieved remarkable success in natural language inference (NLI) tasks. While these models are widely explored, they are hard to interpret and it is often unclear how and why they actually work. In this paper, we take a step toward explaining such deep learning based models through a case study on a popular neural model for NLI. In particular, we propose to interpret the intermediate layers of NLI models by visualizing the saliency of attention and LSTM gating signals. We present several examples for which our methods are able to reveal interesting insights and identify the critical information contributing to the model decisions.