Concept drift is formally defined as the change in joint distribution of a set of input variables X and a target variable y. The two types of drift that are extensively studied are real drift and virtual drift where the former is the change in posterior probabilities p(y|X) while the latter is the change in distribution of X without affecting the posterior probabilities. Many approaches on concept drift detection either assume full availability of data labels, y or handle only the virtual drift. In a streaming environment, the assumption of full availability of data labels, y is questioned. On the other hand, approaches that deal with virtual drift failed to address real drift. Rather than improving the state-of-the-art methods, this paper presents a semi-supervised framework to deal with the challenges above. The objective of the proposed framework is to learn from streaming environment with limited data labels, y and detect real drift concurrently. This paper proposes a novel concept drift detection method utilizing the densities of posterior probabilities in partially labeled streaming environments. Experimental results on both synthetic and realworld datasets show that our proposed semi-supervised framework enables the detection of concept drift in such environment while achieving comparable prediction performance to the state-of-the-art methods.

Finance is a particularly challenging application area for deep learning models due to low noise-to-signal ratio, non-stationarity, and partial observability. Non-deliverable-forwards (NDF), a derivatives contract used in foreign exchange (FX) trading, presents additional difficulty in the form of long-term planning required for an effective selection of start and end date of the contract. In this work, we focus on tackling the problem of NDF tenor selection by leveraging high-dimensional sequential data consisting of spot rates, technical indicators and expert tenor patterns. To this end, we construct a dataset from the Depository Trust & Clearing Corporation (DTCC) NDF data that includes a comprehensive list of NDF volumes and daily spot rates for 64 FX pairs. We introduce WaveATTentionNet (WATTNet), a novel temporal convolution (TCN) model for spatio-temporal modeling of highly multivariate time series, and validate it across NDF markets with varying degrees of dissimilarity between the training and test periods in terms of volatility and general market regimes. The proposed method achieves a significant positive return on investment (ROI) in all NDF markets under analysis, outperforming recurrent and classical baselines by a wide margin. Finally, we propose two orthogonal interpretability approaches to verify noise stability and detect the driving factors of the learned tenor selection strategy.

--In recent years, deep metric learning has achieved promising results in learning high dimensional semantic feature embeddings where the spatial relationships of the feature vectors match the visual similarities of the images. Similarity search for images is performed by determining the vectors with the smallest distances to a query vector . However, high retrieval quality does not depend on the actual distances of the feature vectors, but rather on the ranking order of the feature vectors from similar images. In this paper, we introduce a metric learning algorithm that focuses on identifying and modifying those feature vectors that most strongly affect the retrieval quality. We compute normalized approximated ranks and convert them to similarities by applying a nonlinear transfer function. These similarities are used in a newly proposed loss function that better contracts similar and disperses dissimilar samples. Experiments demonstrate significant improvement over existing deep feature embedding methods on the CUB-200-2011, Cars196, and Stanford Online Products data sets for all embedding sizes.

In this paper, we study the convergence of a class of gradient-based Model-Agnostic Meta-Learning (MAML) methods and characterize their overall computational complexity as well as their best achievable level of accuracy in terms of gradient norm for nonconvex loss functions. In particular, we start with the MAML algorithm and its first order approximation (FO-MAML) and highlight the challenges that emerge in their analysis. By overcoming these challenges not only we provide the first theoretical guarantees for MAML and FO-MAML in nonconvex settings, but also we answer some of the unanswered questions for the implementation of these algorithms including how to choose their learning rate (stepsize) and the batch size for both tasks and datasets corresponding to tasks. In particular, we show that MAML can find an $\epsilon$-first-order stationary point for any positive $\epsilon$ after at most $\mathcal{O}(1/\epsilon^2)$ iterations at the expense of requiring second-order information. We also show that the FO-MAML method which ignores the second-order information required in the update of MAML cannot achieve any small desired level of accuracy, i.e, FO-MAML cannot find an $\epsilon$-first-order stationary point for any positive $\epsilon$. We further propose a new variant of the MAML algorithm called Hessian-free MAML (HF-MAML) which preserves all theoretical guarantees of MAML, without requiring access to the second-order information of loss functions.

Immersive simulations are increasingly used for teaching and training in many societally important arenas including healthcare, disaster response and science education. The interactions of participants in such settings lead to a complex array of emergent outcomes that present challenges for analysis. This paper studies a central element of such an analysis, namely the interpretability of models for inferring structure in time series data. This problem is explored in the context of modeling student interactions in an immersive ecological-system simulation. Unsupervised machine learning is applied to data on system dynamics with the aim of helping teachers determine the effects of students' actions on these dynamics. We address the question of choosing the optimal machine learning model, considering both statistical information criteria and interpretabilty quality. The results of a user study show that the models that are the best understood by people are not those that optimize information theoretic criteria. In addition, a model using a fully Bayesian approach performed well on both statistical measures and on human-subject tests of interpretabilty, making it a good candidate for automated model selection that does not require human-in-the-loop evaluation. The results from this paper are already being used in the classroom and can inform the design of interpretable models for a broad range of socially relevant domains. 1 Introduction There is increasing evidence of the value of multi-person embodied simulations for engaging learners in a variety of applications, such as healthcare, disaster response and education (Alinier et al. 2014; Amir and Gal 2013).

Enterprises around the world, including in India, are increasingly turning to Artificial Intelligence-powered chatbots for customer acquisition, knowledge management and employee engagement. Last September, visa outsourcing and technology services company VFS Global, deployed a chatbot--Viva--offering round-the-clock assistance to visa applicants headed to Australia. Powered by artificial intelligence (AI), the chatbot can decipher patterns from previous interactions, what customers and VFS Global consider as useful information. "Viva radically decreases the response time by replacing an interaction with call centres through chats. Also, it has helped us understand which queries to focus on to improve user experience," said Benjamin Boesch, digital and e-commerce head at VFS Global. In India, Raymond has roped in Applicate IT Solutions' Sellina AI assistant to help, train and engage with the textile giant's 5,000-strong dealer network.

Let's be clear, Artificial Intelligence, in particular in its latest development, deep learning that mimics the way the human mind works, first emerged in America. This gave the U.S. a huge head start over the rest of the world – including China, putting the U.S. firmly in the lead of the race for AI. What Americans didn't develop at home, they bought from Europe. In this respect, two British firms stand out with groundbreaking contributions to AI development: ARM and DeepMind. While all eyes are trained on the AI race between China and America, is there a role left for Europe?

Let's be clear, Artificial Intelligence, in particular in its latest development, deep learning that mimics the way the human mind works, first emerged in America. This gave the U.S. a huge head start over the rest of the world – including China, putting the U.S. firmly in the lead of the race for AI. What Americans didn't develop at home, they bought from Europe. In this respect, two British firms stand out with groundbreaking contributions to AI development: ARM and DeepMind. While all eyes are trained on the AI race between China and America, is there a role left for Europe?

A trio of researchers from Chonnam National University, Nanjing University of Information Science and Technology and the Chinese Academy of Sciences has found that a deep learning convolutional neural network was able to accurately predict El Niño events up to 18 months in advance. In their paper published in the journal Nature, Yoo-Geun Ham, Jeong-Hwan Kim and Jing-Jia Luo, describe their deep learning application, how it was trained and how well it worked in predicting El Niño events. El Niño-Southern Oscillation events are periods during which water warms above normal temperatures in tropical parts of the Pacific. When that warm water moves east, it leads to more rainfall and other weather events, such as hurricanes, in the Americas, and less rain in Australia and Indonesia. Current models can accurately predict such events using data from water temperature gauges spread across the globe up to a year in advance.

Having first appeared on the scene of machine learning in 1986 and artificial neural networks in 2000, the study of deep learning continues to explode with new research, advanced techniques, higher benchmarks, and broader applications. Keeping pace in such an active field with an average of 30 new deep learning papers uploaded to arXiv per day over the previous month is daunting, to say the least. While there are many key deep learning scientists and engineers active today, the following list of 12 researchers and innovators in the field are among the most important – and they so happen to actively share on social media, making their progress and insights much easier to keep up with. So, start paying attention to these 12 top deep learning individuals, and be prepared to expand your understanding and awareness of the incredible advancements deep learning is bringing to science, industry, and society. While it in no way correlates to everyone's contribution to the field, the list is sorted by the number of Twitter followers so you can see who appears to have the most reach today.