In this paper we introduce diagNNose, an open source library for analysing the activations of deep neural networks. diagNNose contains a wide array of interpretability techniques that provide fundamental insights into the inner workings of neural networks… We demonstrate the functionality of diagNNose with a case study on subject-verb agreement within language models. diagNNose is available at https://github.com/i-machine-think/diagnnose. (read more) PDF Abstract  

While humans are aware of their body and capabilities, robots are not. To address this, we present in this paper a neural network architecture that enables a dual-arm robot to get a sense of itself in an environment… Our approach is inspired by human self-awareness developmental levels and serves as the underlying building block for a robot to achieve awareness of itself while carrying out tasks in an environment. We assume that a robot has to know itself before interacting […]

We present a novel approach for image-animation of a source image by a driving video, both depicting the same type of object. We do not assume the existence of pose models and our method is able to animate arbitrary objects without knowledge of the object’s structure… Furthermore, both the driving video and the course image are only seen during test-time. Our method is based on a shared mask generator, which separates the foreground object from its background, and captures the […]

In recent years, there have been immense breakthroughs in Game AI research, particularly with Reinforcement Learning (RL). Despite their success, the underlying games are usually implemented with their own preset environments and game mechanics, thus making it difficult for researchers to prototype different game environments… However, testing the RL agents against a variety of game environments is critical for recent effort to study generalization in RL and avoid the problem of overfitting that may otherwise occur. In this paper, we […]

Deep learning is often criticized by two serious issues which rarely exist in natural nervous systems: overfitting and catastrophic forgetting. It can even memorize randomly labelled data, which has little knowledge behind the instance-label pairs… When a deep network continually learns over time by accommodating new tasks, it usually quickly overwrites the knowledge learned from previous tasks. Referred to as the neural variability, it is well-known in neuroscience that human brain reactions exhibit substantial variability even in response to the […]

In this work, we systematically investigate how well current models of coherence can capture aspects of text implicated in discourse organisation. We devise two datasets of various linguistic alterations that undermine coherence and test model sensitivity to changes in syntax and semantics… We furthermore probe discourse embedding space and examine the knowledge that is encoded in representations of coherence. We hope this study shall provide further insight into how to frame the task and improve models of coherence assessment further. […]

Complying with the EU Regulation on multimodal transportation services requires sharing data on the National Access Points in one of the standards (e.g., NeTEx and SIRI) indicated by the European Commission. These standards are complex and of limited practical adoption… This means that datasets are natively expressed in other formats and require a data translation process for full compliance. This paper describes the solution to turn the authoritative data of three different transport stakeholders from Italy and Spain into a […]