We put forward a video dataset with 5k+ facial bounding box annotations across a troop of 7 western lowland gorillas at Bristol Zoo Gardens. Training on this dataset, we implement and evaluate a standard deep learning pipeline on the task of facially recognising individual gorillas in a zoo environment. We show that a basic YOLOv3-powered application is able to perform identifications at 92% mAP when utilising single frames only. Tracking-by-detection-association and identity voting across short tracklets yields an improved robust performance of 97% mAP. To facilitate easy utilisation for enriching the research capabilities of zoo environments, we publish the code, video dataset, weights, and ground-truth annotations at data.bris.ac.uk.

Predictive process analytics focuses on predicting the future states of running instances of a business process. While advanced machine learning techniques have been used to increase accuracy of predictions, the resulting predictive models lack transparency. Current explainable machine learning methods, such as LIME and SHAP, can be used to interpret black box models. However, it is unclear how fit for purpose these methods are in explaining process predictive models. In this paper, we draw on evaluation measures used in the field of explainable AI and propose functionally-grounded evaluation metrics for assessing explainable methods in predictive process analytics. We apply the proposed metrics to evaluate the performance of LIME and SHAP in interpreting process predictive models built on XGBoost, which has been shown to be relatively accurate in process predictions. We conduct the evaluation using three open source, real-world event logs and analyse the evaluation results to derive insights. The research contributes to understanding the trustworthiness of explainable methods for predictive process analytics as a fundamental and key step towards human user-oriented evaluation.

In this work, we study emergent communication through the lens of cooperative multi-agent behavior in nature. Using insights from animal communication, we propose a spectrum from low-bandwidth (e.g. pheromone trails) to high-bandwidth (e.g. compositional language) communication that is based on the cognitive, perceptual, and behavioral capabilities of social agents. Through a series of experiments with pursuit-evasion games, we identify multi-agent reinforcement learning algorithms as a computational model for the low-bandwidth end of the communication spectrum.

The COVID-19 pandemic has caused international social tension and unrest. Besides the crisis itself, there are growing signs of rising conflict potential of societies around the world. Indicators of global mood changes are hard to detect and direct questionnaires suffer from social desirability biases. However, so-called implicit methods can reveal humans intrinsic desires from e.g. social media texts. We present psychologically validated social unrest predictors and replicate scalable and automated predictions, setting a new state of the art on a recent German shared task dataset. We employ this model to investigate a change of language towards social unrest during the COVID-19 pandemic by comparing established psychological predictors on samples of tweets from spring 2019 with spring 2020. The results show a significant increase of the conflict indicating psychometrics. With this work, we demonstrate the applicability of automated NLP-based approaches to quantitative psychological research.

Analyzing data from the Large Hadron Collider (LHC) present a hyper challenge. A given collision event may result in hundreds of outgoing particles, each with many features (momentum, electric charge, etc.). This hyper variate phase space is then observed by complex multi-channel detectors that are essentially hyperspectral cameras. The LHC detectors have millions of readout channels and dimensionality reduction is essential for data analysis. One natural and nearly lossless reduction is the reconstruction of charged particle trajectories ('tracks'). The innermost layers of the detectors at the LHC are constructed to register the passage of charged particles without significantly altering the particle energy or direction. In the ATLAS and CMS detectors, this is achieved using silicon sensors that are finely segmented in one or two directions and are called strips and pixels, respectively. We will focus on pixels, although our methodology applies more generally. Typically, the first step in a tracking algorithm is the construction of seeds, which are sets of three or more hit pixel clusters that can be used to fit charged-particle trajectories (see e.g.

Machine learning (ML) algorithms may be susceptible to being gamed by individuals with knowledge of the algorithm (a.k.a. Goodhart's law). Such concerns have motivated a surge of recent work on strategic classification where each data point is a self-interested agent and may strategically manipulate his features to induce a more desirable classification outcome for himself. Previous works assume agents have homogeneous preferences and all equally prefer the positive label. This paper generalizes strategic classification to settings where different data points may have different preferences over the classification outcomes. Besides a richer model, this generalization allows us to include evasion attacks in adversarial ML also as a special case of our model where positive [resp. negative] data points prefer the negative [resp. positive] label, and thus for the first time allows strategic and adversarial learning to be studied under the same framework. We introduce the strategic VC-dimension (SVC), which captures the PAC-learnability of a hypothesis class in our general strategic setup. SVC generalizes the notion of adversarial VC-dimension (AVC) introduced recently by Cullina et al. arXiv:1806.01471. We then instantiate our framework for arguably the most basic hypothesis class, i.e., linear classifiers. We fully characterize the statistical learnability of linear classifiers by pinning down its SVC and the computational tractability by pinning down the complexity of the empirical risk minimization problem. Our bound of SVC for linear classifiers also strictly generalizes the AVC bound for linear classifiers in arXiv:1806.01471. Finally, we briefly study the power of randomization in our strategic classification setup. We show that randomization may strictly increase the accuracy in general, but will not help in the special case of adversarial classification under evasion attacks.

Being able to rapidly respond to the changing scenes and traffic situations by generating feasible local paths is of pivotal importance for car autonomy. We propose to train a deep neural network (DNN) to plan feasible and nearly-optimal paths for kinematically constrained vehicles in small constant time. Our DNN model is trained using a novel weakly supervised approach and a gradient-based policy search. On real and simulated scenes and a large set of local planning problems, we demonstrate that our approach outperforms the existing planners with respect to the number of successfully completed tasks. While the path generation time is about 40 ms, the generated paths are smooth and comparable to those obtained from conventional path planners.

Deep learning models trained on large data sets have been widely successful in both vision and language domains. As state-of-the-art deep learning architectures have continued to grow in parameter count so have the compute budgets and times required to train them, increasing the need for compute-efficient methods that parallelize training. Two common approaches to parallelize the training of deep networks have been data and model parallelism. While useful, data and model parallelism suffer from diminishing returns in terms of compute efficiency for large batch sizes. In this paper, we investigate how to continue scaling compute efficiently beyond the point of diminishing returns for large batches through local parallelism, a framework which parallelizes training of individual layers in deep networks by replacing global backpropagation with truncated layer-wise backpropagation. Local parallelism enables fully asynchronous layer-wise parallelism with a low memory footprint, and requires little communication overhead compared with model parallelism. We show results in both vision and language domains across a diverse set of architectures, and find that local parallelism is particularly effective in the high-compute regime. Backpropagation (Rumelhart et al., 1985) is by far the most common method used to train neural networks. Alternatives to backpropagation are typically used only when backpropagation is impractical due to a non-differentiable loss (Schulman et al., 2015), non-smooth loss landscape (Metz et al., 2019), or due to memory and/or compute requirements (Ororbia et al., 2020). This raises the question of whether there are more efficient training strategies, even for models and losses that are considered well matched to training by backpropagation. Much of the work on training large scale models focuses on designing compute infrastructure which makes backpropagation more efficient, despite growing model size (Dean et al., 2012b; Chen et al., 2015; Sergeev & Balso, 2018). One of the most common ways to achieve efficient training of deep neural networks with backpropagation is to scale utilizing data parallelism (Zhang et al., 1989; Chen et al., 2016), training on bigger batch sizes spread across multiple devices. Order determined via coin flip. While data, model, and pipeline parallelism are existing paradigms for parallelizing learning, we investigate another way of parallelizing learning through local layer-wise training shown in (d). Training based on pipeline parallelism has also been introduced, but still requires large batches for efficient training (Petrowski et al., 1993; Ben-Nun & Hoefler, 2018; Huang et al., 2019).

Structure Learning for Bayesian network (BN) is an important problem with extensive research. It plays central roles in a wide variety of applications in Alibaba Group. However, existing structure learning algorithms suffer from considerable limitations in real world applications due to their low efficiency and poor scalability. To resolve this, we propose a new structure learning algorithm LEAST, which comprehensively fulfills our business requirements as it attains high accuracy, efficiency and scalability at the same time. The core idea of LEAST is to formulate the structure learning into a continuous constrained optimization problem, with a novel differentiable constraint function measuring the acyclicity of the resulting graph. Unlike with existing work, our constraint function is built on the spectral radius of the graph and could be evaluated in near linear time w.r.t. the graph node size. Based on it, LEAST can be efficiently implemented with low storage overhead. According to our benchmark evaluation, LEAST runs 1 to 2 orders of magnitude faster than state of the art method with comparable accuracy, and it is able to scale on BNs with up to hundreds of thousands of variables. In our production environment, LEAST is deployed and serves for more than 20 applications with thousands of executions per day. We describe a concrete scenario in a ticket booking service in Alibaba, where LEAST is applied to build a near real-time automatic anomaly detection and root error cause analysis system. We also show that LEAST unlocks the possibility of applying BN structure learning in new areas, such as large-scale gene expression data analysis and explainable recommendation system.

Promising resolutions of the generalization puzzle observe that the actual number of parameters in a deep network is much smaller than naive estimates suggest. The renormalization group is a compelling example of a problem which has very few parameters, despite the fact that naive estimates suggest otherwise. Our central hypothesis is that the mechanisms behind the renormalization group are also at work in deep learning, and that this leads to a resolution of the generalization puzzle. We show detailed quantitative evidence that proves the hypothesis for an RBM, by showing that the trained RBM is discarding high momentum modes. Specializing attention mainly to autoencoders, we give an algorithm to determine the network's parameters directly from the learning data set. The resulting autoencoder almost performs as well as one trained by deep learning, and it provides an excellent initial condition for training, reducing training times by a factor between 4 and 100 for the experiments we considered. Further, we are able to suggest a simple criterion to decide if a given problem can or can not be solved using a deep network.