Machine learning algorithms learn from data and use data from databases that are mutable; therefore, the data and the results of machine learning cannot be fully trusted. Also, the machine learning process is often difficult to automate. A unified analytical framework for trustable machine learning has been presented in the literature. It proposed building a trustable machine learning system by using blockchain technology, which can store data in a permanent and immutable way. In addition, smart contracts on blockchain are used to automate the machine learning process. In the proposed framework, a core machine learning algorithm can have three implementations: server layer implementation, streaming layer implementation, and smart contract implementation. However, there are still open questions. First, the streaming layer usually deploys on edge devices and therefore has limited memory and computing power. How can we run machine learning on the streaming layer? Second, most data that are stored on blockchain are financial transactions, for which fraud detection is often needed. However, in some applications, training data are hard to obtain. Can we build good machine learning models to do fraud detection with limited training data? These questions motivated this paper; which makes two contributions. First, it proposes training a machine learning model on the server layer and saving the model with a special binary data format. Then, the streaming layer can take this blob of binary data as input and score incoming data online. The blob of binary data is very compact and can be deployed on edge devices. Second, the paper presents a new method of synthetic data generation that can enrich the training data set. Experiments show that this synthetic data generation is very effective in applications such as fraud detection in financial data.

--Recent explainability related studies have shown that state-of-the-art DNNs do not always adopt correct evidences to make decisions. It not only hampers their generalization but also makes them less likely to be trusted by end-users. In pursuit of developing more credible DNNs, in this paper we propose CREX, which encourages DNN models to focus more on evidences that actually matter for the task at hand, and to avoid overfitting to data-dependent bias and artifacts. Specifically, CREX regularizes the training process of DNNs with rationales, i.e., a subset of features highlighted by domain experts as justifications for predictions, to enforce DNNs to generate local explanations that conform with expert rationales. Even when rationales are not available, CREX still could be useful by requiring the generated explanations to be sparse. Experimental results on two text classification datasets demonstrate the increased credibility of DNNs trained with CREX. Comprehensive analysis further shows that while CREX does not always improve prediction accuracy on the held-out test set, it significantly increases DNN accuracy on new and previously unseen data beyond test set, highlighting the advantage of the increased credibility. I NTRODUCTION There has been an increasing interest recently in developing explainable deep neural networks (DNNs) [1]-[4]. To this end, a DNN model should be able to provide intuitive explanations for its predictions. Explainability could shed light into the decision making process of DNNs and thus increase their acceptance by end-users. However, explainability alone is insufficient for DNNs to be credible [5], unless the provided explanations conform with the well-established domain knowledge. That is to say, correct evidences should be adopted by the networks to make predictions. The incredibility issue has been observed in various DNN systems.

State-of-the-art machine learning frameworks support a wide variety of design features to enable a flexible machine learning programming interface and to ease the programmability burden on machine learning developers. Identifying and using a performance-optimal setting in feature-rich frameworks, however, involves a non-trivial amount of performance characterization and domain-specific knowledge. This paper takes a deep dive into analyzing the performance impact of key design features and the role of parallelism. The observations and insights distill into a simple set of guidelines that one can use to achieve much higher training and inference speedup. The evaluation results show that our proposed performance tuning guidelines outperform both the Intel and TensorFlow recommended settings by 1.29x and 1.34x, respectively, across a diverse set of real-world deep learning models.

Maintaining good cardiac function for as long as possible is a major concern for healthcare systems worldwide and there is much interest in learning more about the impact of different risk factors on cardiac health. The aim of this study is to analyze the impact of systolic blood pressure (SBP) on cardiac function while preserving the interpretability of the model using known clinical biomarkers in a large cohort of the UK Biobank population. We propose a novel framework that combines deep learning based estimation of interpretable clinical biomarkers from cardiac cine MR data with a variational autoencoder (VAE). The VAE architecture integrates a regression loss in the latent space, which enables the progression of cardiac health with SBP to be learnt. Results on 3,600 subjects from the UK Biobank show that the proposed model allows us to gain important insight into the deterioration of cardiac function with increasing SBP, identify key interpretable factors involved in this process, and lastly exploit the model to understand patterns of positive and adverse adaptation of cardiac function.

--The lack of interpretability remains a barrier to the adoption of deep neural networks. Recently, tree regularization has been proposed to encourage deep neural networks to resemble compact, axis-aligned decision trees without significant compromises in accuracy. However, it may be unreasonable to expect that a single tree can predict well across all possible inputs. In this work, we propose regional tree regularization, which encourages a deep model to be well-approximated by several separate decision trees specific to predefined regions of the input space. Practitioners can define regions based on domain knowledge of contexts where different decision-making logic is needed. Across many datasets, our approach delivers more accurate predictions than simply training separate decision trees for each region, while producing simpler explanations than other neural net regularization schemes without sacrificing predictive power . Two healthcare case studies in critical care and HIV demonstrate how experts can improve understanding of deep models via our approach. I NTRODUCTION Deep models have become the state-of-the-art in applications ranging from image classification [1] to game playing [2], and are poised to advance prediction in real-world domains such as healthcare [3]-[5]. However, understanding when a model's outputs can be trusted and how the model might be improved remains a challenge. Without interpretability, humans are unable to incorporate their domain knowledge and effectively audit predictions. As such, many efforts have been devoted to extracting explanation from deep models post-hoc. Prior work has focused on two opposing regimes. Unfortunately, if the explanation is simple enough to be understandable, then it is unlikely to be faithful to the deep model across all inputs. In contrast, works on local explanation (e.g. These explanations lack generality, as isolated glimpses to the model's behavior can fail to capture larger patterns.

This is important, as more and more enterprises tend to make business decisions based on the user sentiment behind their products as expressed through these videos. Multimodal fusion is considered a key step in multimodal sentiment analysis. Most recent work on multimodal fusion (Poria et al., 2017; Zadeh et al., 2018c) has focused on the strategy of obtaining a multimodal representation from the independent unimodal representations. Our approach takes this strategy one step further, by also requiring that the original unimodal representations be reconstructed from the unified multimodal representation. The motivation behind this is the intuition that different modalities are an expression of the state of the mind. Hence, if we assume that the fused representation is the mind-state/sentiment/emotion, then in our approach we are ensuring that the fused representation can be mapped back to the unimodal representations, which should improve the quality of the multi-modal representation. In this paper, we empirically argue that this is the case by showing that this approach outperforms the state-of-the-art in mul-timodal fusion. We employ a variational autoencoder (V AE) (Kingma and Welling, 2014), where the encoder network generates a latent representation from the unimodal representations.

In real-world question-answering (QA) systems, ill-formed questions, such as wrong words, ill word order, and noisy expressions, are common and may prevent the QA systems from understanding and answering them accurately. In order to eliminate the effect of ill-formed questions, we approach the question refinement task and propose a unified model, QREFINE, to refine the ill-formed questions to well-formed question. The basic idea is to learn a Seq2Seq model to generate a new question from the original one. To improve the quality and retrieval performance of the generated questions, we make two major improvements: 1) To better encode the semantics of ill-formed questions, we enrich the representation of questions with character embedding and the recent proposed contextual word embedding such as BERT, besides the traditional context-free word embeddings; 2) To make it capable to generate desired questions, we train the model with deep reinforcement learning techniques that considers an appropriate wording of the generation as an immediate reward and the correlation between generated question and answer as time-delayed long-term rewards. Experimental results on real-world datasets show that the proposed QREFINE method can generate refined questions with more readability but fewer mistakes than the original questions provided by users. Moreover, the refined questions also significantly improve the accuracy of answer retrieval.

Recent developments in machine-learning algorithms have led to impressive performance increases in many traditional application scenarios of artificial intelligence research. In the area of deep reinforcement learning, deep learning functional architectures are combined with incremental learning schemes for sequential tasks that include interaction-based, but often delayed feedback. Despite their impressive successes, modern machine-learning approaches, including deep reinforcement learning, still perform weakly when compared to flexibly adaptive biological systems in certain naturally occurring scenarios. Such scenarios include transfers to environments different than the ones in which the training took place or environments that dynamically change, both of which are often mastered by biological systems through a capability that we here term "fluid adaptivity" to contrast it from the much slower adaptivity ("crystallized adaptivity") of the prior learning from which the behavior emerged. In this article, we derive and discuss research strategies, based on analyzes of fluid adaptivity in biological systems and its neuronal modeling, that might aid in equipping future artificially intelligent systems with capabilities of fluid adaptivity more similar to those seen in some biologically intelligent systems. A key component of this research strategy is the dynamization of the problem space itself and the implementation of this dynamization by suitably designed flexibly interacting modules.

The use of deep neural networks to make high risk decisions creates a need for global and local explanations so that users and experts have confidence in the modeling algorithms. We introduce a novel technique to find global and local explanations for time series data used in binary classification machine learning systems. We identify the most salient of the original features used by a black box model to distinguish between classes. The explanation can be made on categorical, continuous, and time series data and can be generalized to any binary classification model. The analysis is conducted on time series data to train a long short-term memory deep neural network and uses the time dependent structure of the underlying features in the explanation. The proposed technique attributes weights to features to explain an observations risk of belonging to a class as a multiplicative factor of a base hazard rate. We use a variation of the Cox Proportional Hazards regression, a Generalized Additive Model, to explain the effect of variables upon the probability of an in-class response for a score output from the black box model. The covariates incorporate time dependence structure in the features so the explanation is inclusive of the underlying time series data structure.

User attributes provide rich and useful information for user understanding, yet structured and easy-to-use attributes are often sparsely populated. In this paper, we leverage dialogues with conversational agents, which contain strong suggestions of user information, to automatically extract user attributes. Since no existing dataset is available for this purpose, we apply distant supervision to train our proposed two-stage attribute extractor, which surpasses several retrieval and generation baselines on human evaluation. Meanwhile, we discuss potential applications (e.g., personalized recommendation and dialogue systems) of such extracted user attributes, and point out current limitations to cast light on future work.