Automatic Construction of Fine-Grained Paraphrase Corpora System Using Language Inference Model

Paraphrase detection and generation are important natural language processing (NLP) tasks. Yet the term paraphrase is broad enough to include many fine-grained relations. This leads to different tolerance levels of semantic divergence in the positive paraphrase class among publicly available paraphrase datasets. Such variation can affect the generalisability of paraphrase classification models. It may also impact the predictability of paraphrase generation models. This paper presents a new model which can use few corpora of fine-grained paraphrase relations to construct automatically using language inference models. The fine-grained sentence level paraphrase relations are defined based on word and phrase level counterparts. We demonstrate that the fine-grained labels from our proposed system can make it possible to generate paraphrases at desirable semantic level. The new labels could also contribute to general sentence embedding techniques.

Impact on Inference Model Performance for ML Tasks Using Real-Life Training Data and Synthetic Training Data from GANs

Collecting and labeling of good balanced training data are usually very difficult and challenging under real conditions. In addition to classic modeling methods, Generative Adversarial Networks (GANs) offer a powerful possibility to generate synthetic training data. In this paper, we evaluate the hybrid usage of real-life and generated synthetic training data in different fractions and the effect on model performance. We found that a usage of up to 75% synthetic training data can compensate for both time-consuming and costly manual annotation while the model performance in our Deep Learning (DL) use case stays in the same range compared to a 100% share in hand-annotated real images. Using synthetic training data specifically tailored to induce a balanced dataset, special care can be taken concerning events that happen only on rare occasions and a prompt industrial application of ML models can be executed without too much delay, making these feasible and economically attractive for a wide scope of industrial applications in process and manufacturing industries. Hence, the main outcome of this paper is that our methodology can help to leverage the implementation of many different industrial Machine Learning and Computer Vision applications by making them economically maintainable. It can be concluded that a multitude of industrial ML use cases that require large and balanced training data containing all information that is relevant for the target model can be solved in the future following the findings that are presented in this study.

An active inference model of hierarchical action understanding, learning and imitation

We advance a novel computational model of the acquisition of a hierarchical action repertoire and its use for observation, understanding and motor control. The model is grounded in a principled framework to understand brain and cognition: active inference. We exemplify the functioning of the model by presenting four simulations of a tennis learner who observes a teacher performing tennis shots and forms hierarchical representations of the observed actions - including both actions that are already in her repertoire and novel actions - and finally imitates them. Our simulations that show that the agent’s oculomotor activity implements an active information sampling strategy that permits inferring the kinematics aspects of the observed movement, which lie at the lowest level of the action hierarchy. In turn, this low-level kinematic inference supports higher-level inferences about deeper aspects of the observed actions, such as their proximal goals and intentions. Finally, the inferred action representations can steer imitative motor responses, but interfere with the execution of different actions. Taken together, our simulations show that the same hierarchical active inference model provides a unified account of action observation, understanding, learning and imitation. Finally, our model provides a computational rationale to explain the neurobiological underpinnings of visuomotor cognition, including the multiple routes for action understanding in the dorsal and ventral streams and mirror mechanisms.

Privacy-preserving breast cancer recurrence prediction based on homomorphic encryption and secure two party computation

Protecting patients’ privacy is one of the most important tasks when developing medical artificial intelligence models since medical data is the most sensitive personal data. To overcome this privacy protection issue, diverse privacy-preserving methods have been proposed. We proposed a novel method for privacy-preserving Gated Recurrent Unit (GRU) inference model using privacy enhancing technologies including homomorphic encryption and secure two party computation. The proposed privacy-preserving GRU inference model validated on breast cancer recurrence prediction with 13,117 patients’ medical data. Our method gives reliable prediction result (0.893 accuracy) compared to the normal GRU model (0.895 accuracy). Unlike other previous works, the experiment on real breast cancer data yields almost identical results for privacy-preserving and conventional cases. We also implement our algorithm to shows the realistic end-to-end encrypted breast cancer recurrence prediction.

Probabilistic environmental risk assessment of infectious agents transported by air and with community transmission

PurposeThe paper aims to apply the probabilistic analysis of risks, improve the prediction and control of infections and optimise the use of resources and the knowledge available at all times.Design/methodology/approachFirst, a model based on Bayesian inference, which can be solved with the WinBUGS (Windows interface Bayesian inference Using Gibbs Sampling) simulation software, is described to reduce the uncertainty of the parameter that most influences air transmission: the rate of quanta emitted by the infected. Second, a method for predicting the expected number of infections and combining available resources to reduce parameter is described.FindingsThe results indicate that it is possible to initiate a powerful learning process when all available knowledge is integrated alongside the newly observed data and that it is possible to quantify the interaction between the environment and the spaces, improving the communication process by providing the values in a format that facilitates the objective perception of danger.Research limitations/implicationsThe implementation of the inference model requires access to the spaces where there were infected.Practical implicationsThe current study provides a model and a method to improve the probabilistic analysis of risks, which allows the systematisation of the risk-based management approach to control community transmission caused by infectious agents that use the airway.Social implicationsThe application of the risk assessment and treatment method requires collaboration between the parties that will help the effective implementation of the improvements, such as to verify whether the available resources are sufficient to achieve control.Originality/valueA hierarchical Bayesian inference model is presented to control the uncertainty in the quanta rate. Bayesian inference initiates a learning process to better understand random uncertainty. A method to quantify and communicate risk was also presented, which proposes to decompose the risk into four components to predict the expected number of infected individuals, helping to implement improvement measures, with the resources and knowledge available.

Neurocomputational mechanism of controllability inference under a multi-agent setting

Controllability perception significantly influences motivated behavior and emotion and requires an estimation of one’s influence on an environment. Previous studies have shown that an agent can infer controllability by observing contingency between one’s own action and outcome if there are no other outcome-relevant agents in an environment. However, if there are multiple agents who can influence the outcome, estimation of one’s genuine controllability requires exclusion of other agents’ possible influence. Here, we first investigated a computational and neural mechanism of controllability inference in a multi-agent setting. Our novel multi-agent Bayesian controllability inference model showed that other people’s action-outcome contingency information is integrated with one’s own action-outcome contingency to infer controllability, which can be explained as a Bayesian inference. Model-based functional MRI analyses showed that multi-agent Bayesian controllability inference recruits the temporoparietal junction (TPJ) and striatum. Then, this inferred controllability information was leveraged to increase motivated behavior in the vmPFC. These results generalize the previously known role of the striatum and vmPFC in single-agent controllability to multi-agent controllability, and this generalized role requires the TPJ in addition to the striatum of single-agent controllability to integrate both self- and other-related information. Finally, we identified an innate positive bias toward the self during the multi-agent controllability inference, which facilitated behavioral adaptation under volatile controllability. Furthermore, low positive bias and high negative bias were associated with increased daily feelings of guilt. Our results provide a mechanism of how our sense of controllability fluctuates due to other people in our lives, which might be related to social learned helplessness and depression.

A Bayesian neural network predicts the dissolution of compact planetary systems

We introduce a Bayesian neural network model that can accurately predict not only if, but also when a compact planetary system with three or more planets will go unstable. Our model, trained directly from short N-body time series of raw orbital elements, is more than two orders of magnitude more accurate at predicting instability times than analytical estimators, while also reducing the bias of existing machine learning algorithms by nearly a factor of three. Despite being trained on compact resonant and near-resonant three-planet configurations, the model demonstrates robust generalization to both nonresonant and higher multiplicity configurations, in the latter case outperforming models fit to that specific set of integrations. The model computes instability estimates up to 105 times faster than a numerical integrator, and unlike previous efforts provides confidence intervals on its predictions. Our inference model is publicly available in the SPOCK (https://github.com/dtamayo/spock) package, with training code open sourced (https://github.com/MilesCranmer/bnn_chaos_model).