Deep reinforcement learning (DRL) breaks through the bottlenecks of traditional reinforcement learning (RL) with the help of the perception capability of deep learning and has been widely applied in real-world problems.While model-free RL, as a class of efficient DRL methods, performs the learning of state representations simultaneously with policy learning in an end-to-end manner when facing large-scale continuous state and action spaces. However, training such a large policy model requires a large number of trajectory samples and training time. On the other hand, the learned policy often fails to generalize to large-scale action spaces, especially for the continuous action spaces. To address this issue, in this paper we propose an efficient policy learning method in latent state and action spaces. More specifically, we extend the idea of state representations to action representations for better policy generalization capability. Meanwhile, we divide the whole learning task into learning with the large-scale representation models in an unsupervised manner and learning with the small-scale policy model in the RL manner.The small policy model facilitates policy learning, while not sacrificing generalization and expressiveness via the large representation model. Finally,the effectiveness of the proposed method is demonstrated by MountainCar,CarRacing and Cheetah experiments.
Explainable artificial intelligence (XAI) methods are expected to improve trust during human-AI interactions, provide tools for model analysis and extend human understanding of complex problems. Explanation-supervised training allows to improve explanation quality by training self-explaining XAI models on ground truth or human-generated explanations. However, existing explanation methods have limited expressiveness and interoperability due to the fact that only single explanations in form of node and edge importance are generated. To that end we propose the novel multi-explanation graph attention network (MEGAN). Our fully differentiable, attention-based model features multiple explanation channels, which can be chosen independently of the task specifications. We first validate our model on a synthetic graph regression dataset. We show that for the special single explanation case, our model significantly outperforms existing post-hoc and explanation-supervised baseline methods. Furthermore, we demonstrate significant advantages when using two explanations, both in quantitative explanation measures as well as in human interpretability. Finally, we demonstrate our model's capabilities on multiple real-world datasets. We find that our model produces sparse high-fidelity explanations consistent with human intuition about those tasks and at the same time matches state-of-the-art graph neural networks in predictive performance, indicating that explanations and accuracy are not necessarily a trade-off.
A high-quality 3D reconstruction of a scene from a collection of 2D images can be achieved through offline/online mapping methods. In this paper, we explore active mapping from the perspective of implicit representations, which have recently produced compelling results in a variety of applications. One of the most popular implicit representations - Neural Radiance Field (NeRF), first demonstrated photorealistic rendering results using multi-layer perceptrons, with promising offline 3D reconstruction as a by-product of the radiance field. More recently, researchers also applied this implicit representation for online reconstruction and localization (i.e. implicit SLAM systems). However, the study on using implicit representation for active vision tasks is still very limited. In this paper, we are particularly interested in applying the neural radiance field for active mapping and planning problems, which are closely coupled tasks in an active system. We, for the first time, present an RGB-only active vision framework using radiance field representation for active 3D reconstruction and planning in an online manner. Specifically, we formulate this joint task as an iterative dual-stage optimization problem, where we alternatively optimize for the radiance field representation and path planning. Experimental results suggest that the proposed method achieves competitive results compared to other offline methods and outperforms active reconstruction methods using NeRFs.
This is a theoretical paper, as a companion paper of the plenary talk for the same conference ISAIC 2022. In contrast to conscious learning, which develops a single network for a normal life and is the main topic of the plenary talk, it is necessary to address the currently widespread approach, so-called "Deep Learning". Although "Deep Learning" may use different learning modes, including supervised, reinforcement and adversarial modes, almost all "Deep Learning" projects apparently suffer from the same misconduct, called "data deletion" and "test on training data". Consequently, Deep Learning almost always was not tested at all. Why? The so-called "test set" was used in the Post-Selection step of the training stage. This paper establishes a theorem that a simple method called Pure-Guess Nearest Neighbor (PGNN) reaches any required errors on validation set and test set, including zero-error requirements, through the "Deep Learning" misconduct, as long as the test set is in the possession of the author and both the amount of storage space and the time of training are finite but unbounded. However, Deep Learning methods, like the PGNN method, apparently are not generalizable since they have never been tested at all by a valid test set.
Multiphysics problems such as multicomponent diffusion, phase transformations in multiphase systems and alloy solidification involve numerical solution of a coupled system of nonlinear partial differential equations (PDEs). Numerical solutions of these PDEs using mesh-based methods require spatiotemporal discretization of these equations. Hence, the numerical solutions are often sensitive to discretization parameters and may have inaccuracies (resulting from grid-based approximations). Moreover, choice of finer mesh for higher accuracy make these methods computationally expensive. Neural network-based PDE solvers are emerging as robust alternatives to conventional numerical methods because these use machine learnable structures that are grid-independent, fast and accurate. However, neural network based solvers require large amount of training data, thus affecting their generalizabilty and scalability. These concerns become more acute for coupled systems of time-dependent PDEs. To address these issues, we develop a new neural network based framework that uses encoder-decoder based conditional Generative Adversarial Networks with ConvLSTM layers to solve a system of Cahn-Hilliard equations. These equations govern microstructural evolution of a ternary alloy undergoing spinodal decomposition when quenched inside a three-phase miscibility gap. We show that the trained models are mesh and scale-independent, thereby warranting application as effective neural operators.
Underwater acoustic monitoring systems record many hours of audio data for marine research, making fast and reliable non-causal signal detection paramount. Such detectors assist in reducing the amount of labor required for signal annotations, which often contain large portions devoid of signals. Cetacean vocalization detection based on spectral entropy is investigated as a means of vocalization discovery. Previous techniques using spectral entropy (SE) mostly consider time-frequency enhancement of the entropy measure, and utilize the STFT as its time-frequency (TF) decomposition. SE methods also requires the user to set a detection threshold manually, which call for knowledge of the produced entropy measures. This paper considers median filtering as a simple, effective way to provide temporal stabilization to the entropy measure, and considers the CWT as an alternative TF decomposition. K-means clustering is used to determine the threshold required to accurately separate the signal/no-signal entropy measures, resulting in a one-dimensional, two-class classification problem. The class means are used to perform pseudo-probabilistic soft class assignment, which is a useful metric in algorithmic development. The effect of median filtering, signal-to-noise ratio and the chosen TF decomposition are investigated. The proposed method shows a significant improvement in detection accuracy and specificity, while also providing a more interpretable detection threshold setting via soft class assignment.
In this paper, we propose a novel uniform generalization bound on the time and inverse temperature for stochastic gradient Langevin dynamics (SGLD) in a non-convex setting. While previous works derive their generalization bounds by uniform stability, we use Rademacher complexity to make our generalization bound independent of the time and inverse temperature. Using Rademacher complexity, we can reduce the problem to derive a generalization bound on the whole space to that on a bounded region and therefore can remove the effect of the time and inverse temperature from our generalization bound. As an application of our generalization bound, an evaluation on the effectiveness of the simulated annealing in a non-convex setting is also described. For the sample size $n$ and time $s$, we derive evaluations with orders $\sqrt{n^{-1} \log (n+1)}$ and $|(\log)^4(s)|^{-1}$, respectively. Here, $(\log)^4$ denotes the $4$ times composition of the logarithmic function.
Recent work has shown that machine learning (ML) models can be trained to accurately forecast the dynamics of unknown chaotic dynamical systems. Such ML models can be used to produce both short-term predictions of the state evolution and long-term predictions of the statistical patterns of the dynamics (``climate''). Both of these tasks can be accomplished by employing a feedback loop, whereby the model is trained to predict forward one time step, then the trained model is iterated for multiple time steps with its output used as the input. In the absence of mitigating techniques, however, this technique can result in artificially rapid error growth, leading to inaccurate predictions and/or climate instability. In this article, we systematically examine the technique of adding noise to the ML model input during training as a means to promote stability and improve prediction accuracy. Furthermore, we introduce Linearized Multi-Noise Training (LMNT), a regularization technique that deterministically approximates the effect of many small, independent noise realizations added to the model input during training. Our case study uses reservoir computing, a machine-learning method using recurrent neural networks, to predict the spatiotemporal chaotic Kuramoto-Sivashinsky equation. We find that reservoir computers trained with noise or with LMNT produce climate predictions that appear to be indefinitely stable and have a climate very similar to the true system, while reservoir computers trained without regularization are unstable. Compared with other types of regularization that yield stability in some cases, we find that both short-term and climate predictions from reservoir computers trained with noise or with LMNT are substantially more accurate. Finally, we show that the deterministic aspect of our LMNT regularization facilitates fast hyperparameter tuning when compared to training with noise.
Despite the recent success of deep learning architectures, person re-identification (ReID) remains a challenging problem in real-word applications. Several unsupervised single-target domain adaptation (STDA) methods have recently been proposed to limit the decline in ReID accuracy caused by the domain shift that typically occurs between source and target video data. Given the multimodal nature of person ReID data (due to variations across camera viewpoints and capture conditions), training a common CNN backbone to address domain shifts across multiple target domains, can provide an efficient solution for real-time ReID applications. Although multi-target domain adaptation (MTDA) has not been widely addressed in the ReID literature, a straightforward approach consists in blending different target datasets, and performing STDA on the mixture to train a common CNN. However, this approach may lead to poor generalization, especially when blending a growing number of distinct target domains to train a smaller CNN. To alleviate this problem, we introduce a new MTDA method based on knowledge distillation (KD-ReID) that is suitable for real-time person ReID applications. Our method adapts a common lightweight student backbone CNN over the target domains by alternatively distilling from multiple specialized teacher CNNs, each one adapted on data from a specific target domain. Extensive experiments conducted on several challenging person ReID datasets indicate that our approach outperforms state-of-art methods for MTDA, including blending methods, particularly when training a compact CNN backbone like OSNet. Results suggest that our flexible MTDA approach can be employed to design cost-effective ReID systems for real-time video surveillance applications.
Recently there has been significant interest in measuring time-varying functional connectivity (TVC) between different brain regions using resting-state functional magnetic resonance imaging (rs-fMRI) data. One way to assess the relationship between signals from different brain regions is to measure their phase synchronization (PS) across time. However, this requires the \textit{a priori} choice of type and cut-off frequencies for the bandpass filter needed to perform the analysis. Here we explore alternative approaches based on the use of various mode decomposition (MD) techniques that circumvent this issue. These techniques allow for the data driven decomposition of signals jointly into narrow-band components at different frequencies, thus fulfilling the requirements needed to measure PS. We explore several variants of MD, including empirical mode decomposition (EMD), bivariate EMD (BEMD), noise-assisted multivariate EMD (na-MEMD), and introduce the use of multivariate variational mode decomposition (MVMD) in the context of estimating time-varying PS. We contrast the approaches using a series of simulations and application to rs-fMRI data. Our results show that MVMD outperforms other evaluated MD approaches, and further suggests that this approach can be used as a tool to reliably investigate time-varying PS in rs-fMRI data.