Existing dialog system models require extensive human annotations and are difficult to generalize to different tasks. The recent success of large pre-trained language models such as BERT and GPT -2 (Devlin et al., 2019; Radford et al., 2019) have suggested the effectiveness of incorporating language priors in downstream NLP tasks. However, how much pre-trained language models can help dialog response generation is still under exploration. In this paper, we propose a simple, general, and effective framework: Alternating Recurrent Dialog Model (ARDM). ARDM models each speaker separately and takes advantage of the large pre-trained language model. It requires no supervision from human annotations such as belief states or dialog acts to achieve effective conversations. ARDM outperforms or is on par with state-of-the-art methods on two popular task-oriented dialog datasets: CamRest676 and MultiWOZ. Moreover, we can generalize ARDM to more challenging, non-collaborative tasks such as persuasion. In persuasion tasks, ARDM is capable of generating humanlike responses to persuade people to donate to a charity. It has been a longstanding ambition for artificial intelligence researchers to create an intelligent conversational agent that can generate humanlike responses. Recently data-driven dialog models are more and more popular. However, most current state-of-the-art approaches still rely heavily on extensive annotations such as belief states and dialog acts (Lei et al., 2018). However, dialog content can vary considerably in different dialog tasks. Having a different intent or dialog act annotation scheme for each task is costly. For some tasks, it is even impossible, such as open-domain social chat. Thus, it is difficult to utilize these methods on challenging dialog tasks, such as persuasion and negotiation, where dialog states and acts are difficult to annotate.

This article presents WekaCoin, a peer-to-peer cryptocurrency based on a new distributed consensus protocol called Proof-of-Learning. Proof-of-learning achieves distributed consensus by ranking machine learning systems for a given task. The aim of this protocol is to alleviate the computational waste involved in hashing-based puzzles and to create a public distributed and verifiable database of state-of-the-art machine learning models and experiments.

US: Telecommunication infrastructure owners have some of the most widely distributed and remote assets to build, maintain, and repair. With approximately 27,000 distributed sites and 6,000 communication towers under management, Telstra is Australia's leading telecommunication service provider. Traditional inspection methods of towers involve manually taking photographs and measurements. This requires workers climbing on the towers, usually in remote areas, making the process dangerous, inefficient, costly, and time-consuming. In 2017, Telstra engaged SiteSee to perform automated as-built and condition assessment reports by applying machine learning and object recognition technology to 3D reality meshes.

A team of researchers led by CSIRO's Data61, the data and digital specialist arm of Australia's national science agency, have developed a novel technique that could assist psychiatrists and other clinicians to diagnose and characterize complex mental health disorders, potentially enabling more effective treatments. Announced today at D61 LIVE in Sydney, the researchers revealed that using a simple computer game and artificial intelligence techniques, they were able to identify behavioral patterns in subjects with depression and bipolar disorder, down to subtle individual differences in each group. The study included 101 participants: 34 with depression, 33 with bipolar disorder, and a control group of 34 subjects. The computer game presents individuals with two choices, and tracks their behavior as they respond. The complex data collected from the game is analyzed through artificial neural networks--brain-inspired systems intended to replicate the way that humans learn--which are able to disentangle the nuanced behavioral differences between healthy individuals, and those with depression or bipolar disorder.

The use of "nudges" in policymaking has been a major trend since the UK launched the world's first government-embedded behavioural insights unit in 2010. But governments around the world, from Denmark to Singapore, have been using principles from behavioural science to influence citizens since at least the 1960s. That's according to a new World Bank report, Behavioural Science Around the World, which highlights 10 countries that are pioneering the use of behavioural insights: Australia, Canada, Denmark, France, Germany, the Netherlands, Peru, Singapore, the UK and the US. The World Bank report looks at how these teams are integrated into government, which projects they're working on and how they are run -- and, most importantly, which experiments have worked. It predicts that in the future, behavioural insights units will benefit from artificial intelligence, machine learning and virtual reality the same way they've gained from advancements in open data and e-government.

Generative Adversarial Networks have been shown to be powerful in generating content. To this end, they have been studied intensively in the last few years. Nonetheless, training these networks requires solving a saddle point problem that is difficult to solve and slowly converging. Motivated from techniques in the registration of point clouds and by the fluid flow formulation of mass transport, we investigate a new formulation that is based on strict minimization, without the need for the maximization. The formulation views the problem as a matching problem rather than an adversarial one and thus allows us to quickly converge and obtain meaningful metrics in the optimization path.

Fraud causes substantial costs and losses for companies and clients in the finance and insurance industries. Examples are fraudulent credit card transactions or fraudulent claims. It has been estimated that roughly $10$ percent of the insurance industry's incurred losses and loss adjustment expenses each year stem from fraudulent claims. The rise and proliferation of digitization in finance and insurance have lead to big data sets, consisting in particular of text data, which can be used for fraud detection. In this paper, we propose architectures for text embeddings via deep learning, which help to improve the detection of fraudulent claims compared to other machine learning methods. We illustrate our methods using a data set from a large international health insurance company. The empirical results show that our approach outperforms other state-of-the-art methods and can help make the claims management process more efficient. As (unstructured) text data become increasingly available to economists and econometricians, our proposed methods will be valuable for many similar applications, particularly when variables have a large number of categories as is typical for example of the International Classification of Disease (ICD) codes in health economics and health services.

Cell detection and cell type classification from biomedical images play an important role for high-throughput imaging and various clinical application. While classification of single cell sample can be performed with standard computer vision and machine learning methods, analysis of multi-label samples (region containing congregating cells) is more challenging, as separation of individual cells can be difficult (e.g. touching cells) or even impossible (e.g. overlapping cells). As multi-instance images are common in analyzing Red Blood Cell (RBC) for Sickle Cell Disease (SCD) diagnosis, we develop and implement a multi-instance cell detection and classification framework to address this challenge. The framework firstly trains a region proposal model based on Region-based Convolutional Network (RCNN) to obtain bounding-boxes of regions potentially containing single or multiple cells from input microscopic images, which are extracted as image patches. High-level image features are then calculated from image patches through a pre-trained Convolutional Neural Network (CNN) with ResNet-50 structure. Using these image features inputs, six networks are then trained to make multi-label prediction of whether a given patch contains cells belonging to a specific cell type. As the six networks are trained with image patches consisting of both individual cells and touching/overlapping cells, they can effectively recognize cell types that are presented in multi-instance image samples. Finally, for the purpose of SCD testing, we train another machine learning classifier to predict whether the given image patch contains abnormal cell type based on outputs from the six networks. Testing result of the proposed framework shows that it can achieve good performance in automatic cell detection and classification.

Traditional sequence-to-sequence (seq2seq) models and other variations of the attention-mechanism such as hierarchical attention have been applied to the text summarization problem. Though there is a hierarchy in the way humans use language by forming paragraphs from sentences and sentences from words, hierarchical models have usually not worked that much better than their traditional seq2seq counterparts. This effect is mainly because either the hierarchical attention mechanisms are too sparse using hard attention or noisy using soft attention. In this paper, we propose a method based on extracting the highlights of a document; a key concept that is conveyed in a few sentences. In a typical text summarization dataset consisting of documents that are 800 tokens in length (average), capturing long-term dependencies is very important, e.g., the last sentence can be grouped with the first sentence of a document to form a summary. LSTMs (Long Short-Term Memory) proved useful for machine translation. However, they often fail to capture long-term dependencies while modeling long sequences. To address these issues, we have adapted Neural Semantic Encoders (NSE) to text summarization, a class of memory-augmented neural networks by improving its functionalities and proposed a novel hierarchical NSE that outperforms similar previous models significantly. The quality of summarization was improved by augmenting linguistic factors, namely lemma, and Part-of-Speech (PoS) tags, to each word in the dataset for improved vocabulary coverage and generalization. The hierarchical NSE model on factored dataset outperformed the state-of-the-art by nearly 4 ROUGE points. We further designed and used the first GPU-based self-critical Reinforcement Learning model.

With the emergence of onboard vision processing for areas such as the internet of things (IoT), edge computing and autonomous robots, there is increasing demand for computationally efficient convolutional neural network (CNN) models to perform real-time object detection on resource constraints hardware devices. Tiny-YOLO is generally considered as one of the faster object detectors for low-end devices and is the basis for our work. Our experiments on this network have shown that Tiny-YOLO can achieve 0.14 frames per second(FPS) on the Raspberry Pi 3 B, which is too slow for soccer playing autonomous humanoid robots detecting goal and ball objects. In this paper we propose an adaptation to the YOLO CNN model named xYOLO, that can achieve object detection at a speed of 9.66 FPS on the Raspberry Pi 3 B. This is achieved by trading an acceptable amount of accuracy, making the network approximately 70 times faster than Tiny-YOLO. Greater inference speed-ups were also achieved on a desktop CPU and GPU. Additionally we contribute an annotated Darknet dataset for goal and ball detection.