Recent developments within deep learning are relevant for nonlinear system identification problems. In this paper, we establish connections between the deep learning and the system identification communities. It has recently been shown that convolutional architectures are at least as capable as recurrent architectures when it comes to sequence modeling tasks. Inspired by these results we explore the explicit relationships between the recently proposed temporal convolutional network (TCN) and two classic system identification model structures; Volterra series and block-oriented models. We end the paper with an experimental study where we provide results on two real-world problems, the well-known Silverbox dataset and a newer dataset originating from ground vibration experiments on an F-16 fighter aircraft.

Data-driven techniques for identifying disease subtypes using medical records can greatly benefit the management of patients' health and unravel the underpinnings of diseases. Clinical patient records are typically collected from disparate sources and result in high-dimensional data comprising of multiple likelihoods with noisy and missing values. Probabilistic methods capable of analysing large-scale patient records have a central role in biomedical research and are expected to become even more important when data-driven personalised medicine will be established in clinical practise. In this work we propose an unsupervised, generative model that can identify clustering among patients in a latent space while making use of all available data (i.e. in a heterogeneous data setting with noisy and missing values). We make use of the Gaussian process latent variable models (GPLVM) and deep neural networks to create a non-linear dimensionality reduction technique for heterogeneous data. The effectiveness of our model is demonstrated on clinical data of Parkinson's disease patients treated at the HUS Helsinki University Hospital. We demonstrate sub-groups from the heterogeneous patient data, evaluate the robustness of the findings, and interpret cluster characteristics.

A recent trend observed in traditionally challenging fields such as computer vision and natural language processing has been the significant performance gains shown by deep learning (DL). In many different research fields, DL models have been evolving rapidly and become ubiquitous. Despite researchers' excitement, unfortunately, most software developers are not DL experts and oftentimes have a difficult time following the booming DL research outputs. As a result, it usually takes a significant amount of time for the latest superior DL models to prevail in industry. This issue is further exacerbated by the common use of sundry incompatible DL programming frameworks, such as Tensorflow, PyTorch, Theano, etc. To address this issue, we propose a system, called Model Asset Exchange (MAX), that avails developers of easy access to state-of-the-art DL models. Regardless of the underlying DL programming frameworks, it provides an open source Python library (called the MAX framework) that wraps DL models and unifies programming interfaces with our standardized RESTful APIs. These RESTful APIs enable developers to exploit the wrapped DL models for inference tasks without the need to fully understand different DL programming frameworks. Using MAX, we have wrapped and open-sourced more than 30 state-of-the-art DL models from various research fields, including computer vision, natural language processing and signal processing, etc. In the end, we selectively demonstrate two web applications that are built on top of MAX, as well as the process of adding a DL model to MAX.

These can generate data samples using probabilistic constructs that include NNs. This has provoked a strong impact within the deep learning community as it allowed dealing with many unsupervised learning problems. See [2] for a recent review of these models. Along these lines, a new set of software tools have appeared, building on top of standard deep learning frameworks, in order to accommodate probabilistic models containing NNs [5, 3, 4]. These tools usually fall under the umbrella term probabilistic programming languages (PPLs) [7], and provide support for methods for reasoning about complex probabilistic models. Some examples are Edward2/TFP [8, 3], Pyro [4], etc. 3. Software Framework The main features of InferPy are: (i) Its simple API allows easy prototyping of probabilistic models including NNs; (ii) Unlike Edward2/TFP, it is not require to have a strong background in the inference methods available (Variational Inference [1, 2] and Monte Carlo methods [9]) as many details are hidden to the user; (iii) Parallelization details are also hidden to the user: InferPy runs seamlessly on CPUs and GPUs. InferPy can be seen as an upper layer for working with Edward2/TFP. Thus, models that can be defined in InferPy are those that can be defined using Edward2/TFP. InferPy is distributed as open-software (Apache-2.0)

While deep learning has achieved remarkable results on various applications, it is usually data hungry and struggles to learn over non-stationary data stream. To solve these two limits, the deep learning model should not only be able to learn from a few of data, but also incrementally learn new concepts from data stream over time without forgetting the previous knowledge. Limited literature simultaneously address both problems. In this work, we propose a novel approach, MetaCL, which enables neural networks to effectively learn meta knowledge from low-shot data stream without catastrophic forgetting. MetaCL trains a model to exploit the intrinsic feature of data (i.e. meta knowledge) and dynamically penalize the important model parameters change to preserve learned knowledge. In this way, the deep learning model can efficiently obtain new knowledge from small volume of data and still keep high performance on previous tasks. MetaCL is conceptually simple, easy to implement and model-agnostic. We implement our method on three recent regularization-based methods. Extensive experiments show that our approach leads to state-of-the-art performance on image classification benchmarks.

Commonsense reasoning aims to empower machines with the human ability to make presumptions about ordinary situations in our daily life. In this paper, we propose a textual inference framework for answering commonsense questions, which effectively utilizes external, structured commonsense knowledge graphs to perform explainable inferences. The framework first grounds a question-answer pair from the semantic space to the knowledge-based symbolic space as a schema graph, a related sub-graph of external knowledge graphs. It represents schema graphs with a novel knowledge-aware graph network module named KagNet, and finally scores answers with graph representations. Our model is based on graph convolutional networks and LSTMs, with a hierarchical path-based attention mechanism. The intermediate attention scores make it transparent and interpretable, which thus produce trustworthy inferences. Using ConceptNet as the only external resource for Bert-based models, we achieved state-of-the-art performance on the CommonsenseQA, a large-scale dataset for commonsense reasoning.

Classification and differentiation of small pathological objects may greatly vary among human raters due to differences in training, expertise and their consistency over time. In a radiological setting, objects commonly have high within-class appearance variability whilst sharing certain characteristics across different classes, making their distinction even more difficult. As an example, markers of cerebral small vessel disease, such as enlarged perivascular spaces (EPVS) and lacunes, can be very varied in their appearance while exhibiting high inter-class similarity, making this task highly challenging for human raters. In this work, we investigate joint models of individual rater behaviour and multi-rater consensus in a deep learning setting, and apply it to a brain lesion object-detection task. Results show that jointly modelling both individual and consensus estimates leads to significant improvements in performance when compared to directly predicting consensus labels, while also allowing the characterization of human-rater consistency.

While Reinforcement Learning (RL) approaches lead to significant achievements in a variety of areas in recent history, natural language tasks remained mostly unaffected, due to the compositional and combinatorial nature that makes them notoriously hard to optimize. With the emerging field of Text-Based Games (TBGs), researchers try to bridge this gap. Inspired by the success of RL algorithms on Atari games, the idea is to develop new methods in a restricted game world and then gradually move to more complex environments. Previous work in the area of TBGs has mainly focused on solving individual games. We, however, consider the task of designing an agent that not just succeeds in a single game, but performs well across a whole family of games, sharing the same theme. In this work, we present our deep RL agent--LeDeepChef--that shows generalization capabilities to never-before-seen games of the same family with different environments and task descriptions. The agent participated in Microsoft Research's "First TextWorld Problems: A Language and Reinforcement Learning Challenge" and outperformed all but one competitor on the final test set. The games from the challenge all share the same theme, namely cooking in a modern house environment, but differ significantly in the arrangement of the rooms, the presented objects, and the specific goal (recipe to cook). To build an agent that achieves high scores across a whole family of games, we use an actor-critic framework and prune the action-space by using ideas from hierarchical reinforcement learning and a specialized module trained on a recipe database.

Abstractive summarization approaches based on Reinforcement Learning (RL) have recently been proposed to overcome classical likelihood maximization. RL enables to consider complex, possibly non-differentiable, metrics that globally assess the quality and relevance of the generated outputs. ROUGE, the most used summarization metric, is known to suffer from bias towards lexical similarity as well as from suboptimal accounting for fluency and readability of the generated abstracts. W e thus explore and propose alternative evaluation measures: the reported human-evaluation analysis shows that the proposed metrics, based on Question Answering, favorably compares to ROUGE - with the additional property of not requiring reference summaries. Training a RL-based model on these metrics leads to improvements (both in terms of human or automated metrics) over current approaches that use ROUGE as a reward.

Jacob Rafati, David C. Noelle Electrical Engineering and Computer Scinence Computational Cognitive Neuroscience Laboratory University of California, Merced 5200 North Lake Road, Merced, CA 95343 USA.Abstract Reinforcement learning (RL) algorithms allow artificial agents to improve their selection of actions to increase rewarding experiences in their environments. Temporal Di ff erence (TD) Learning - a model-free RL method - is a leading account of the midbrain dopamine system and the basal ganglia in reinforcement learning. These algorithms typically learn a mapping from the agent's current sensed state to a selected action (known as a policy function) via learning a value function (expected future rewards). TD Learning methods have been very successful on a broad range of control tasks, but learning can become intractably slow as the state space of the environment grows. This has motivated methods that learn internal representations of the agent's state, e ffectively reducing the size of the state space and restructuring state representations in order to support generalization. However, TD Learning coupled with an artificial neural network, as a function approximator, has been shown to fail to learn some fairly simple control tasks, challenging this explanation of reward-based learning. We hypothesize that such failures do not arise in the brain because of the ubiquitous presence of lateral inhibition in the cortex, producing sparse distributed internal representations that support the learning of expected future reward. The sparse conjunctive representations can avoid catastrophic interference while still supporting generalization. We provide support for this conjecture through computational simulations, demonstrating the benefits of learned sparse representations for three problematic classic control tasks: Puddle-world, Mountain-car, and Acrobot. Introduction Reinforcement learning (RL) - a class of machine learning problems - is learning how to map situations to actions so as to maximize numerical reward signals received during the experiences that an artificial agent has as it interacts with its environment (Sutton and Barto, 1998). The agent may also be seen as having a goal (or goals) related to the state of the environment. Humans and nonhuman animals' capability of learning highly complex skills by reinforcing appropriate behaviors with reward and the role of midbrain dopamine system in reward-based learning has been well described by a class of a model-free RL, called T emporal Difference (TD) Learning (Montague et al., 1996; Schultz et al., 1997). While TD Learning, by itself, certainly does not explain all observed RL phenomena, increasing evidence suggests that it is key to the brain's adaptive nature (Dayan and Niv, 2008). One of the challenges that arise in RL in real-world problems is that the state space can be very large.