The use of deep neural networks (DNNs) in safety-critical applications like mobile health and autonomous driving is challenging due to numerous model-inherent shortcomings. These shortcomings are diverse and range from a lack of generalization over insufficient interpretability to problems with malicious inputs. Cyber-physical systems employing DNNs are therefore likely to suffer from safety concerns. In recent years, a zoo of state-of-the-art techniques aiming to address these safety concerns has emerged. This work provides a structured and broad overview of them. We first identify categories of insufficiencies to then describe research activities aiming at their detection, quantification, or mitigation. Our paper addresses both machine learning experts and safety engineers: The former ones might profit from the broad range of machine learning topics covered and discussions on limitations of recent methods. The latter ones might gain insights into the specifics of modern ML methods. We moreover hope that our contribution fuels discussions on desiderata for ML systems and strategies on how to propel existing approaches accordingly.

Path tracking system plays a key technology in autonomous driving. The system should be driven accurately along the lane and be careful not to cause any inconvenience to passengers. To address such tasks, this paper proposes hybrid tracker based optimal path tracking system. By applying a deep learning based lane detection algorithm and a designated fast lane fitting algorithm, this paper developed a lane processing algorithm that shows a match rate with actual lanes with minimal computational cost. In addition, three modified path tracking algorithms were designed using the GPS based path or the vision based path. In the driving system, a match rate for the correct ideal path does not necessarily represent driving stability. This paper proposes hybrid tracker based optimal path tracking system by applying the concept of an observer that selects the optimal tracker appropriately in complex road environments. The driving stability has been studied in complex road environments such as straight road with multiple 3-way junctions, roundabouts, intersections, and tunnels. Consequently, the proposed system experimentally showed the high performance with consistent driving comfort by maintaining the vehicle within the lanes accurately even in the presence of high complexity of road conditions. Code will be available in https://github.com/DGIST-ARTIV.

The L3DAS21 Challenge is aimed at encouraging and fostering collaborative research on machine learning for 3D audio signal processing, with particular focus on 3D speech enhancement (SE) and 3D sound localization and detection (SELD). Alongside with the challenge, we release the L3DAS21 dataset, a 65 hours 3D audio corpus, accompanied with a Python API that facilitates the data usage and results submission stage. Usually, machine learning approaches to 3D audio tasks are based on single-perspective Ambisonics recordings or on arrays of single-capsule microphones. We propose, instead, a novel multichannel audio configuration based multiple-source and multiple-perspective Ambisonics recordings, performed with an array of two first-order Ambisonics microphones. To the best of our knowledge, it is the first time that a dual-mic Ambisonics configuration is used for these tasks. We provide baseline models and results for both tasks, obtained with state-of-the-art architectures: FaSNet for SE and SELDNet for SELD. This report is aimed at providing all needed information to participate in the L3DAS21 Challenge, illustrating the details of the L3DAS21 dataset, the challenge tasks and the baseline models.

Recurrent meta reinforcement learning (meta-RL) agents are agents that employ a recurrent neural network (RNN) for the purpose of "learning a learning algorithm". After being trained on a pre-specified task distribution, the learned weights of the agent's RNN are said to implement an efficient learning algorithm through their activity dynamics, which allows the agent to quickly solve new tasks sampled from the same distribution. However, due to the black-box nature of these agents, the way in which they work is not yet fully understood. In this study, we shed light on the internal working mechanisms of these agents by reformulating the meta-RL problem using the Partially Observable Markov Decision Process (POMDP) framework. We hypothesize that the learned activity dynamics is acting as belief states for such agents. Several illustrative experiments suggest that this hypothesis is true, and that recurrent meta-RL agents can be viewed as agents that learn to act optimally in partially observable environments consisting of multiple related tasks. This view helps in understanding their failure cases and some interesting model-based results reported in the literature.

Automatic hate speech detection in online social networks is an important open problem in Natural Language Processing (NLP). Hate speech is a multidimensional issue, strongly dependant on language and cultural factors. Despite its relevance, research on this topic has been almost exclusively devoted to English. Most supervised learning resources, such as labeled datasets and NLP tools, have been created for this same language. Considering that a large portion of users worldwide speak in languages other than English, there is an important need for creating efficient approaches for multilingual hate speech detection. In this work we propose to address the problem of multilingual hate speech detection from the perspective of transfer learning. Our goal is to determine if knowledge from one particular language can be used to classify other language, and to determine effective ways to achieve this. We propose a hate specific data representation and evaluate its effectiveness against general-purpose universal representations most of which, unlike our proposed model, have been trained on massive amounts of data. We focus on a cross-lingual setting, in which one needs to classify hate speech in one language without having access to any labeled data for that language. We show that the use of our simple yet specific multilingual hate representations improves classification results. We explain this with a qualitative analysis showing that our specific representation is able to capture some common patterns in how hate speech presents itself in different languages. Our proposal constitutes, to the best of our knowledge, the first attempt for constructing multilingual specific-task representations. Despite its simplicity, our model outperformed the previous approaches for most of the experimental setups. Our findings can orient future solutions toward the use of domain-specific representations.

In this paper, we address the problem of image captioning specifically for molecular translation where the result would be a predicted chemical notation in InChI format for a given molecular structure. Current approaches mainly follow rule-based or CNN RNN based methodology. However, they seem to underperform on noisy images and images with small number of distinguishable features. To overcome this, we propose an end-to-end transformer model. When compared to attention-based techniques, our proposed model outperforms on molecular datasets.

We present the Zero Resource Speech Challenge 2021, which asks participants to learn a language model directly from audio, without any text or labels. The challenge is based on the Libri-light dataset, which provides up to 60k hours of audio from English audio books without any associated text. We provide a pipeline baseline system consisting on an encoder based on contrastive predictive coding (CPC), a quantizer ($k$-means) and a standard language model (BERT or LSTM). The metrics evaluate the learned representations at the acoustic (ABX discrimination), lexical (spot-the-word), syntactic (acceptability judgment) and semantic levels (similarity judgment). We present an overview of the eight submitted systems from four groups and discuss the main results.

Large pre-trained language models (LMs) have demonstrated remarkable ability as few-shot learners. However, their success hinges largely on scaling model parameters to a degree that makes it challenging to train and serve. In this paper, we propose a new approach, named as EFL, that can turn small LMs into better few-shot learners. The key idea of this approach is to reformulate potential NLP task into an entailment one, and then fine-tune the model with as little as 8 examples. We further demonstrate our proposed method can be: (i) naturally combined with an unsupervised contrastive learning-based data augmentation method; (ii) easily extended to multilingual few-shot learning. A systematic evaluation on 18 standard NLP tasks demonstrates that this approach improves the various existing SOTA few-shot learning methods by 12\%, and yields competitive few-shot performance with 500 times larger models, such as GPT-3.

Modelling the dynamics of urban venues is a challenging task as it is multifaceted in nature. Demand is a function of many complex and nonlinear features such as neighborhood composition, real-time events, and seasonality. Recent advances in Graph Convolutional Networks (GCNs) have had promising results as they build a graphical representation of a system and harness the potential of deep learning architectures. However, there has been limited work using GCNs in a temporal setting to model dynamic dependencies of the network. Further, within the context of urban environments, there has been no prior work using dynamic GCNs to support venue demand analysis and prediction. In this paper, we propose a novel deep learning framework which aims to better model the popularity and growth of urban venues. Using a longitudinal dataset from location technology platform Foursquare, we model individual venues and venue types across London and Paris. First, representing cities as connected networks of venues, we quantify their structure and note a strong community structure in these retail networks, an observation that highlights the interplay of cooperative and competitive forces that emerge in local ecosystems of retail businesses. Next, we present our deep learning architecture which integrates both spatial and topological features into a temporal model which predicts the demand of a venue at the subsequent time-step. Our experiments demonstrate that our model can learn spatio-temporal trends of venue demand and consistently outperform baseline models. Relative to state-of-the-art deep learning models, our model reduces the RSME by ~ 28% in London and ~ 13% in Paris. Our approach highlights the power of complex network measures and GCNs in building prediction models for urban environments. The model could have numerous applications within the retail sector to better model venue demand and growth.

Graph neural networks (GNNs) are deep learning architectures for machine learning problems on graphs. It has recently been shown that the expressiveness of GNNs can be characterised precisely by the combinatorial Weisfeiler-Leman algorithms and by finite variable counting logics. The correspondence has even led to new, higher-order GNNs corresponding to the WL algorithm in higher dimensions. The purpose of this paper is to explain these descriptive characterisations of GNNs.