Deep neural networks are known to be overconfident when applied to out-of-distribution (OOD) inputs which clearly do not belong to any class. This is a problem in safety-critical applications since a reliable assessment of the uncertainty of a classifier is a key property, allowing the system to trigger human intervention or to transfer into a safe state. In this paper, we aim for certifiable worst case guarantees for OOD detection by enforcing not only low confidence at the OOD point but also in an $l_\infty$-ball around it. For this purpose, we use interval bound propagation (IBP) to upper bound the maximal confidence in the $l_\infty$-ball and minimize this upper bound during training time. We show that non-trivial bounds on the confidence for OOD data generalizing beyond the OOD dataset seen at training time are possible. Moreover, in contrast to certified adversarial robustness which typically comes with significant loss in prediction performance, certified guarantees for worst case OOD detection are possible without much loss in accuracy.

Neurons in real brains are enormously complex computational units. Among other things, they're responsible for transforming inbound electro-chemical vectors into outbound action potentials, updating the strengths of intermediate synapses, regulating their own internal states, and modulating the behavior of other nearby neurons. One could argue that these cells are the only things exhibiting any semblance of real intelligence. It is odd, therefore, that the machine learning community has, for so long, relied upon the assumption that this complexity can be reduced to a simple sum and fire operation. We ask, might there be some benefit to substantially increasing the computational power of individual neurons in artificial systems? To answer this question, we introduce Deep Artificial Neurons (DANs), which are themselves realized as deep neural networks. Conceptually, we embed DANs inside each node of a traditional neural network, and we connect these neurons at multiple synaptic sites, thereby vectorizing the connections between pairs of cells. We demonstrate that it is possible to meta-learn a single parameter vector, which we dub a neuronal phenotype, shared by all DANs in the network, which facilitates a meta-objective during deployment. Here, we isolate continual learning as our meta-objective, and we show that a suitable neuronal phenotype can endow a single network with an innate ability to update its synapses with minimal forgetting, using standard backpropagation, without experience replay, nor separate wake/sleep phases. We demonstrate this ability on sequential non-linear regression tasks.

We present DeepMind Lab2D, a scalable environment simulator for artificial intelligence research that facilitates researcher-led experimentation with environment design. DeepMind Lab2D was built with the specific needs of multi-agent deep reinforcement learning researchers in mind, but it may also be useful beyond that particular subfield.

We present Model-Predictive Interaction Primitives -- a robot learning framework for assistive motion in human-machine collaboration tasks which explicitly accounts for biomechanical impact on the human musculoskeletal system. First, we extend Interaction Primitives to enable predictive biomechanics: the prediction of future biomechanical states of a human partner conditioned on current observations and intended robot control signals. In turn, we leverage this capability within a model-predictive control strategy to identify the future ergonomic and biomechanical ramifications of potential robot actions. Optimal control trajectories are selected so as to minimize future physical impact on the human musculoskeletal system. We empirically demonstrate that our approach minimizes knee or muscle forces via generated control actions selected according to biomechanical cost functions. Experiments are performed in synthetic and real-world experiments involving powered prosthetic devices.

Literature on self-assessment in machine learning mainly focuses on the production of well-calibrated algorithms through consensus frameworks i.e. calibration is seen as a problem. Yet, we observe that learning to be properly confident could behave like a powerful regularization and thus, could be an opportunity to improve performance.Precisely, we show that used within a framework of action detection, the learning of a self-assessment score is able to improve the whole action localization process.Experimental results show that our approach outperforms the state-of-the-art on two action detection benchmarks. On THUMOS14 dataset, the mAP at tIoU@0.5 is improved from 42.8\% to 44.6\%, and from 50.4\% to 51.7\% on ActivityNet1.3 dataset. For lower tIoU values, we achieve even more significant improvements on both datasets.

Pedestrian Attribute Recognition (PAR) has aroused extensive attention due to its important role in video surveillance scenarios. In most cases, the existence of a particular attribute is strongly related to a partial region. Recent works design complicated modules, e.g., attention mechanism and proposal of body parts to localize the attribute corresponding region. These works further prove that localization of attribute specific regions precisely will help in improving performance. However, these part-information-based methods are still not accurate as well as increasing model complexity which makes it hard to deploy on realistic applications. In this paper, we propose a Deep Template Matching based method to capture body parts features with less computation. Further, we also proposed an auxiliary supervision method that use human pose keypoints to guide the learning toward discriminative local cues. Extensive experiments show that the proposed method outperforms and has lower computational complexity, compared with the state-of-the-art approaches on large-scale pedestrian attribute datasets, including PETA, PA-100K, RAP, and RAPv2 zs.

Deep learning classifiers are assisting humans in making decisions and hence the user's trust in these models is of paramount importance. Trust is often a function of constant behavior. From an AI model perspective it means given the same input the user would expect the same output, especially for correct outputs, or in other words consistently correct outputs. This paper studies a model behavior in the context of periodic retraining of deployed models where the outputs from successive generations of the models might not agree on the correct labels assigned to the same input. We formally define consistency and correct-consistency of a learning model. We prove that consistency and correct-consistency of an ensemble learner is not less than the average consistency and correct-consistency of individual learners and correct-consistency can be improved with a probability by combining learners with accuracy not less than the average accuracy of ensemble component learners. To validate the theory using three datasets and two state-of-the-art deep learning classifiers we also propose an efficient dynamic snapshot ensemble method and demonstrate its value.

The classification of different fine hand movements from EEG signals represents a relevant research challenge, e.g., in brain-computer interface applications for motor rehabilitation. Here, we analyzed two different datasets where fine hand movements (touch, grasp, palmar and lateral grasp) were performed in a self-paced modality. We trained and tested a newly proposed convolutional neural network (CNN), and we compared its classification performance into respect to two well-established machine learning models, namely, a shrinked-LDA and a Random Forest. Compared to previous literature, we took advantage of the knowledge of the neuroscience field, and we trained our CNN model on the so-called Movement Related Cortical Potentials (MRCPs)s. They are EEG amplitude modulations at low frequencies, i.e., (0.3, 3) Hz, that have been proved to encode several properties of the movements, e.g., type of grasp, force level and speed. We showed that CNN achieved good performance in both datasets and they were similar or superior to the baseline models. Also, compared to the baseline, our CNN requires a lighter and faster pre-processing procedure, paving the way for its possible use in an online modality, e.g., for many brain-computer interface applications.

Robust and safe self-driving in complex and dynamic environments is quite challenging due to the requirement of scalable driving policies against the wide variety of traffic scenarios (e,g., road topologies, traffic rules and interaction with road agents). In this area, traditional modular frameworks scale poorly in new environments, and require tremendous and iterative hand-tuning of rules and parameters to maintain performance in all foreseeable scenarios. Recently, deep-learning based self-driving methods have shown promising results with better generalization capability but less hand engineering effort. However, most of the previous methods are trained and evaluated in limited and simple environments with scattered tasks, such as lane-following, autonomous braking and conditional driving. In this paper, we propose a graph-based deep network to achieve unified and scalable self-driving in diverse dynamic environments. The extensive evaluation results show that our model can safely navigate the vehicle in a large variety of urban, rural, and highway areas with dense traffic while obeying traffic rules. Specifically, more than 7,500 km of closed-loop driving evaluation is conducted in dynamic simulation environments, in which our method can handle complex driving situations, and achieve higher success rates (73.5%-83.2%) and driving scores than the baselines.

Advanced technologies are increasingly used in criminal activities. Identifying, preventing and fighting modern crime demands the implementation of pioneering technologies and methods. The EU-funded AIDA project is focussing on cybercrime and terrorism by approaching specific issues related to law enforcement agencies (LEAs) using pioneering machine learning and artificial intelligence methods. The project will deliver a descriptive and predictive data analytics platform and related tools which will prevent, identify, analyse and combat cybercrime and terrorist activities. The platform is based on the fundamental technology applied to Big Data analytics provided with AI and deep learning techniques expanded and tailored with additional crime-specific capabilities and tools.