Assistive robotics and particularly robot coaches may be very helpful for rehabilitation healthcare. In this context, we propose a method based on Gaussian Process Latent Variable Model (GP-LVM) to transfer knowledge between a physiotherapist, a robot coach and a patient. Our model is able to map visual human body features to robot data in order to facilitate the robot learning and imitation. In addition , we propose to extend the model to adapt robots' understanding to patient's physical limitations during the assessment of rehabilitation exercises. Experimental evaluation demonstrates promising results for both robot imitation and model adaptation according to the patients' limitations.

Network pruning is widely used for reducing the heavy computational cost of deep models. A typical pruning algorithm is a three-stage pipeline, i.e., training (a large model), pruning and fine-tuning. During pruning, according to a certain criterion, redundant weights are pruned and important weights are kept to best preserve the accuracy. In this work, we make several surprising observations which contradict common beliefs. For all the six state-of-the-art pruning algorithms we examined, fine-tuning a pruned model only gives comparable or even worse performance than training that model with randomly initialized weights. For pruning algorithms which assume a predefined target network architecture, one can get rid of the full pipeline and directly train the target network from scratch. Our observations are consistent for a wide variety of pruning algorithms with multiple network architectures, datasets, and tasks. Our results have several implications: 1) training a large, over-parameterized model is not necessary to obtain an efficient final model, 2) learned "important" weights of the large model are not necessarily useful for the small pruned model, 3) the pruned architecture itself, rather than a set of inherited "important" weights, is what leads to the efficiency benefit in the final model, which suggests that some pruning algorithms could be seen as performing network architecture search. Over-parameterization is a widely-recognized property of deep neural networks (Denton et al., 2014; Ba & Caruana, 2014), which leads to high computational cost and high memory footprint.

Data augmentation is commonly used to encode invariances in learning methods. However, this process is often performed in an inefficient manner, as artificial examples are created by applying a number of transformations to all points in the training set. The resulting explosion of the dataset size can be an issue in terms of storage and training costs, as well as in selecting and tuning the optimal set of transformations to apply. In this work, we demonstrate that it is possible to significantly reduce the number of data points included in data augmentation while realizing the same accuracy and invariance benefits of augmenting the entire dataset. We propose a novel set of subsampling policies, based on model influence and loss, that can achieve a 90% reduction in augmentation set size while maintaining the accuracy gains of standard data augmentation.

We study a general problem of allocating limited resources to heterogeneous customers over time under model uncertainty. Each type of customer can be serviced using different actions, each of which stochastically consumes some combination of resources, and returns different rewards for the resources consumed. We consider a general model where the resource consumption distribution associated with each (customer type, action)-combination is not known, but is consistent and can be learned over time. In addition, the sequence of customer types to arrive over time is arbitrary and completely unknown. We overcome both the challenges of model uncertainty and customer heterogeneity by judiciously synthesizing two algorithmic frameworks from the literature: inventory balancing, which "reserves" a portion of each resource for high-reward customer types which could later arrive, and online learning, which shows how to "explore" the resource consumption distributions of each customer type under different actions. We define an auxiliary problem, which allows for existing competitive ratio and regret bounds to be seamlessly integrated. Furthermore, we show that the performance guarantee generated by our framework is tight, that is, we provide an information-theoretic lower bound which shows that both the loss from competitive ratio and the loss for regret are relevant in the combined problem. Finally, we demonstrate the efficacy of our algorithms on a publicly available hotel data set. Our framework is highly practical in that it requires no historical data (no fitted customer choice models, nor forecasting of customer arrival patterns) and can be used to initialize allocation strategies in fast-changing environments.

Abstract-- Feature Selection (FS) plays an important role in learning and classification tasks. The object of FS is to select the relevant and non-redundant features. Considering the huge amount number of features in real-world applications, FS methods using batch learning technique can't resolve big data problem especially when data arrive sequentially. In this paper, we propose an online feature selection system which resolves this problem. More specifically, we treat the problem of online supervised feature selection for binary classification as a decision-making problem. A philosophical vision to this problem leads to a hybridization between two important domains: feature selection using online learning technique (OFS) and automated negotiation (AN). The proposed OFS system called MOANOFS (Multi-Objective Automated Negotiation based Online Feature Selection) uses two levels of decision. In the first level, from n learners (or OFS methods), we decide which are the k trustful ones (with high confidence or trust value). These elected k learners will participate in the second level. In this level, we integrate our proposed Multilateral Automated Negotiation based OFS (MANOFS) method to decide finally which is the best solution or which are relevant features. We show that MOANOFS system is applicable to different domains successfully and achieves high accuracy with several real-world applications. Index Terms-- Feature selection, online learning, multi-objective automated negotiation, trust, classification, big data. URING the last three decades, Feature Selection (FS) has been extensively studied in Data Mining [1], [2], Pattern Classification [3], [4] and Machine Learning [5], [6]. FS is defined as the process of selecting a subset of relevant features and removing the redundant ones from a dataset for building effective prediction models. In recent years, an enormous increase in data (news, medical imaging) has been observed which allows an increase in redundant information. Even worse, the redundancy of irrelevant data has a negative impact on the performance of classification methods associated. With the rapid development of the Internet, current tremendous amounts of data up to millions or billions, can be collected for training machine learning models.

To start implementing AI, you should have the basic knowledge of traditional algorithms and concepts. Artificial intelligence has been a thrill for the world's minds for decades. The quest for the creation of an artificial brain was inspired by the natural processes of the human brain. AI prototyping was represented in multiple science fiction books and movies. Gradually, the idea turned into a scientific concept and triggered the creation of practical intelligent technologies.

As Innovation Lead for Precision Medicine at Innovate UK I am sometimes asked about the best STEM subjects to study, usually by parents wanting to help their children select the best university courses. Something they're really interested in, I have tended to say, but now add that something involving AI (Artificial Intelligence) might be a very wise choice. AI's nothing new, but now seems on the verge of making a big impact in clinical settings, reflected in our competition applications in the area of precision medicine. There are many ways AI can play a role in the medical arena, where being able to find patterns and associations in large data sets is fundamental to developing new technologies and services. These large data sets include disparate patient information, such as the increasing levels of genetic information we will have about patients, and linking it to phenotypic information (observable physical properties e.g.

The summit will focus on understanding the financially excluded segment, use of alternative data (geospatial, social media, mobile footprint, psychographics) in developing credit risk scoring algorithm, and building simpler AI-enabled financial delivery interfaces. The Summit is scheduled to hold on Wednesday, 10 October 2018 at the Oriental Hotel, Victoria Island, Lagos and with the theme, "New Algorithms for the Financially Excluded Segment". This is a broad based stakeholder session focused on understanding emerging trends and advanced data analytics use cases applied to issues of financial inclusion. The one-day Summit will be followed by a five-day residential, all-expenses-paid Artificial Intelligence Bootcamp and Hackathon on emerging trends in machine learning and deep learning between 10 and 14 October 2018. The intent of the bootcamp and hackathon is to build world-class capacity in advanced data analytics, upskill financial inclusion data analysts and researchers in emerging best practices, and to support the development of contextually relevant algorithm and tech innovation.

Leading Valamis' product development, our Chief Technology Officer Dmitry "Dima" Kudinov has spent the past six years researching AI and the best applications to support lifelong learning. With years of research under his belt, Dima talks about the power of AI to personalize learning, the benefits of AI supported lifelong learning, and what this will mean for the future of Valamis product development. First of all, I'm very excited about the progress made in Natural Language Understanding. Of course, this topic is nothing new, but in recent time there has been significant progress made thanks to the accessibility of greater computing power, richer data sets for training, and the creation of more sophisticated algorithms. This improvement with text-based input has allowed a new way of interaction between people and systems in the form of chatbots to emerge. Backed by an even more exciting progress in Speech to Text and Text to Speech conversions, chatbots now have personalities, and they can engage in voice dialog with people.

A relatively small group of savvy executives have strategies in place to harness new business process automation technologies and thereby advance their digital transformation agenda. Meanwhile, a much larger group is closely following the market leaders, to explore their lessons-learned from pilot projects. According to the latest worldwide market study by 451 Research, new survey results suggest most organisations are adopting or considering artificial intelligence (AI) and machine learning (ML) due to its commercial growth benefits, rather than the potential to cut jobs. Almost 50 percent of their survey respondents have deployed or plan to deploy machine learning in their organisations within the next 12 months. Therefore, this paints a more optimistic picture of machine learning adoption than is often portrayed by other industry analysts. "Out of many possible benefits we presented to our survey respondents, 49 percent cited gaining competitive advantage as the most significant benefit they have received from the technology," said Nick Patience, vice president at 451 Research.