In a recent work arXiv:2008.08601, Halverson, Maiti and Stoner proposed a description of neural networks in terms of a Wilsonian effective field theory. The infinite-width limit is mapped to a free field theory, while finite $N$ corrections are taken into account by interactions (non-Gaussian terms in the action). In this paper, we study two related aspects of this correspondence. First, we comment on the concepts of locality and power-counting in this context. Indeed, these usual space-time notions may not hold for neural networks (since inputs can be arbitrary), however, the renormalization group provides natural notions of locality and scaling. Moreover, we comment on several subtleties, for example, that data components may not have a permutation symmetry: in that case, we argue that random tensor field theories could provide a natural generalization. Second, we improve the perturbative Wilsonian renormalization from arXiv:2008.08601 by providing an analysis in terms of the nonperturbative renormalization group using the Wetterich-Morris equation. An important difference with usual nonperturbative RG analysis is that only the effective (IR) 2-point function is known, which requires setting the problem with care. Our aim is to provide a useful formalism to investigate neural networks behavior beyond the large-width limit (i.e.~far from Gaussian limit) in a nonperturbative fashion. A major result of our analysis is that changing the standard deviation of the neural network weight distribution can be interpreted as a renormalization flow in the space of networks. We focus on translations invariant kernels and provide preliminary numerical results.

Incentive salience attribution can be understood as a psychobiological process ascribing relevance to potentially rewarding objects and actions. Despite being an important component of the motivational process guiding our everyday behaviour its study in naturalistic contexts is not straightforward. Here we propose a methodology based on artificial neural networks (ANNs) for approximating latent states produced by this process in situations where large volumes of behavioural data are available but no strict experimental control is possible. Leveraging knowledge derived from theoretical and computational accounts of incentive salience attribution we designed an ANN for estimating duration and intensity of future interactions between individuals and a series of video games in a large-scale ($N> 3 \times 10^6$) longitudinal dataset. Through model comparison and inspection we show that our approach outperforms competing ones while also generating a representation that well approximate some of the functions of attributed incentive salience. We discuss our findings with reference to the adopted theoretical and computational frameworks and suggest how our methodology could be an initial step for estimating attributed incentive salience in large scale behavioural studies.

Compressed sensing [23, 15] has enabled reductions to the number of measurements needed for successful reconstruction in a variety of imaging inverse problems. In particular, it has led to shorter scan times for magnetic resonance imaging (MRI) [58, 86], and most MRI vendors have released products leveraging this framework to accelerate clinical workflows. Despite their successes, sparsity-based methods are limited by the achievable acceleration rates, as the sparsity assumptions are either hand-crafted or are limited to simple learned sparse codes [68, 69]. More recently, deep learning techniques have been used as powerful data-driven reconstruction methods for inverse problems [47, 64]. There are two broad families of deep learning inversion techniques [64]: end-to-end supervised and distribution-learning approaches. End-to-end supervised techniques use a training set of measured images and deploy convolutional neural networks (CNNs) and other architectures to learn the inverse mapping from measurements to image. Network architectures that include both CNN blocks and the imaging forward model have grown in popularity, as they combine deep learning with the compressed sensing optimization framework, see e.g.

Deep learning has achieved great success in a wide spectrum of multimedia applications such as image classification, natural language processing and multimodal data analysis. Recent years have seen the development of many deep learning frameworks that provide a high-level programming interface for users to design models, conduct training and deploy inference. However, it remains challenging to build an efficient end-to-end multimedia application with most existing frameworks. Specifically, in terms of usability, it is demanding for non-experts to implement deep learning models, obtain the right settings for the entire machine learning pipeline, manage models and datasets, and exploit external data sources all together. Further, in terms of adaptability, elastic computation solutions are much needed as the actual serving workload fluctuates constantly, and scaling the hardware resources to handle the fluctuating workload is typically infeasible. To address these challenges, we introduce SINGA-Easy, a new deep learning framework that provides distributed hyper-parameter tuning at the training stage, dynamic computational cost control at the inference stage, and intuitive user interactions with multimedia contents facilitated by model explanation. Our experiments on the training and deployment of multi-modality data analysis applications show that the framework is both usable and adaptable to dynamic inference loads. We implement SINGA-Easy on top of Apache SINGA and demonstrate our system with the entire machine learning life cycle.

Neural networks can be powerful function approximators, which are able to model high-dimensional feature distributions from a subset of examples drawn from the target distribution. Naturally, they perform well at generalizing within the limits of their target function, but they often fail to generalize outside of the explicitly learned feature space. It is therefore an open research topic whether and how neural network-based architectures can be deployed for systematic reasoning. Many studies have shown evidence for poor generalization, but they often work with abstract data or are limited to single-channel input. Humans, however, learn and interact through a combination of multiple sensory modalities, and rarely rely on just one. To investigate compositional generalization in a multimodal setting, we generate an extensible dataset with multimodal input sequences from simulation. We investigate the influence of the underlying training data distribution on compostional generalization in a minimal LSTM-based network trained in a supervised, time continuous setting. We find compositional generalization to fail in simple setups while improving with the number of objects, actions, and particularly with a lot of color overlaps between objects. Furthermore, multimodality strongly improves compositional generalization in settings where a pure vision model struggles to generalize.

Machine learning (ML) models are known to be vulnerable to adversarial examples. Applications of ML to voice biometrics authentication are no exception. Yet, the implications of audio adversarial examples on these real-world systems remain poorly understood given that most research targets limited defenders who can only listen to the audio samples. Conflating detectability of an attack with human perceptibility, research has focused on methods that aim to produce imperceptible adversarial examples which humans cannot distinguish from the corresponding benign samples. We argue that this perspective is coarse for two reasons: 1. Imperceptibility is impossible to verify; it would require an experimental process that encompasses variations in listener training, equipment, volume, ear sensitivity, types of background noise etc, and 2. It disregards pipeline-based detection clues that realistic defenders leverage. This results in adversarial examples that are ineffective in the presence of knowledgeable defenders. Thus, an adversary only needs an audio sample to be plausible to a human. We thus introduce surreptitious adversarial examples, a new class of attacks that evades both human and pipeline controls. In the white-box setting, we instantiate this class with a joint, multi-stage optimization attack. Using an Amazon Mechanical Turk user study, we show that this attack produces audio samples that are more surreptitious than previous attacks that aim solely for imperceptibility. Lastly we show that surreptitious adversarial examples are challenging to develop in the black-box setting.

Deep neural networks have been applied to a wide range of problems across different application domains with great success. Recently, research into combinatorial optimization problems in particular has generated much interest in the machine learning community. In this work, we develop deep learning models to predict the chromatic number and maximum clique size of graphs, both of which represent classical NP-complete combinatorial optimization problems encountered in graph theory. The neural networks are trained using the most basic representation of the graph, the adjacency matrix, as opposed to undergoing complex domain-specific feature engineering. The experimental results show that deep neural networks, and in particular convolutional neural networks, obtain strong performance on this problem.

There is a warning light for the loss of plant habitats worldwide that entails concerted efforts to conserve plant biodiversity. Thus, plant species classification is of crucial importance to address this environmental challenge. In recent years, there is a considerable increase in the number of studies related to plant taxonomy. While some researchers try to improve their recognition performance using novel approaches, others concentrate on computational optimization for their framework. In addition, a few studies are diving into feature extraction to gain significantly in terms of accuracy. In this paper, we propose an effective method for the leaf recognition problem. In our proposed approach, a leaf goes through some pre-processing to extract its refined color image, vein image, xy-projection histogram, handcrafted shape, texture features, and Fourier descriptors. These attributes are then transformed into a better representation by neural network-based encoders before a support vector machine (SVM) model is utilized to classify different leaves. Overall, our approach performs a state-of-the-art result on the Flavia leaf dataset, achieving the accuracy of 99.58\% on test sets under random 10-fold cross-validation and bypassing the previous methods. We also release our codes\footnote{Scripts are available at \url{https://github.com/dinhvietcuong1996/LeafRecognition}} for contributing to the research community in the leaf classification problem.

Recent advances in Natural Language Processing (NLP), and specifically automated Question Answering (QA) systems, have demonstrated both impressive linguistic fluency and a pernicious tendency to reflect social biases. In this study, we introduce Q-Pain, a dataset for assessing bias in medical QA in the context of pain management, one of the most challenging forms of clinical decision-making. Along with the dataset, we propose a new, rigorous framework, including a sample experimental design, to measure the potential biases present when making treatment decisions. We demonstrate its use by assessing two reference Question-Answering systems, GPT-2 and GPT-3, and find statistically significant differences in treatment between intersectional race-gender subgroups, thus reaffirming the risks posed by AI in medical settings, and the need for datasets like ours to ensure safety before medical AI applications are deployed.

Deep Generative Models (DGMs) allow users to synthesize data from complex, high-dimensional manifolds. Industry applications of DGMs include data augmentation to boost performance of (semi-)supervised machine learning, or to mitigate fairness or privacy concerns. Large-scale DGMs are notoriously hard to train, requiring expert skills, large amounts of data and extensive computational resources. Thus, it can be expected that many enterprises will resort to sourcing pre-trained DGMs from potentially unverified third parties, e.g.~open source model repositories. As we show in this paper, such a deployment scenario poses a new attack surface, which allows adversaries to potentially undermine the integrity of entire machine learning development pipelines in a victim organization. Specifically, we describe novel training-time attacks resulting in corrupted DGMs that synthesize regular data under normal operations and designated target outputs for inputs sampled from a trigger distribution. Depending on the control that the adversary has over the random number generation, this imposes various degrees of risk that harmful data may enter the machine learning development pipelines, potentially causing material or reputational damage to the victim organization. Our attacks are based on adversarial loss functions that combine the dual objectives of attack stealth and fidelity. We show its effectiveness for a variety of DGM architectures (Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs)) and data domains (images, audio). Our experiments show that - even for large-scale industry-grade DGMs - our attack can be mounted with only modest computational efforts. We also investigate the effectiveness of different defensive approaches (based on static/dynamic model and output inspections) and prescribe a practical defense strategy that paves the way for safe usage of DGMs.