For real-world deployments, it is critical to allow robots to navigate in complex environments autonomously. Traditional methods usually maintain an internal map of the environment, and then design several simple rules, in conjunction with a localization and planning approach, to navigate through the internal map. These approaches often involve a variety of assumptions and prior knowledge. In contrast, recent reinforcement learning (RL) methods can provide a model-free, self-learning mechanism as the robot interacts with an initially unknown environment, but are expensive to deploy in real-world scenarios due to inefficient exploration. In this paper, we focus on efficient navigation with the RL technique and combine the advantages of these two kinds of methods into a rule-based RL (RuRL) algorithm for reducing the sample complexity and cost of time. First, we use the rule of wall-following to generate a closed-loop trajectory. Second, we employ a reduction rule to shrink the trajectory, which in turn effectively reduces the redundant exploration space. Besides, we give the detailed theoretical guarantee that the optimal navigation path is still in the reduced space. Third, in the reduced space, we utilize the Pledge rule to guide the exploration strategy for accelerating the RL process at the early stage. Experiments conducted on real robot navigation problems in hex-grid environments demonstrate that RuRL can achieve improved navigation performance.
The performance of machine learning algorithms heavily relies on the availability of a large amount of training data. However, in reality, data usually reside in distributed parties such as different institutions and may not be directly gathered and integrated due to various data policy constraints. As a result, some parties may suffer from insufficient data available for training machine learning models. In this paper, we propose a multi-party dual learning (MPDL) framework to alleviate the problem of limited data with poor quality in an isolated party. Since the knowledge sharing processes for multiple parties always emerge in dual forms, we show that dual learning is naturally suitable to handle the challenge of missing data, and explicitly exploits the probabilistic correlation and structural relationship between dual tasks to regularize the training process. We introduce a feature-oriented differential privacy with mathematical proof, in order to avoid possible privacy leakage of raw features in the dual inference process. The approach requires minimal modifications to the existing multi-party learning structure, and each party can build flexible and powerful models separately, whose accuracy is no less than non-distributed self-learning approaches. The MPDL framework achieves significant improvement compared with state-of-the-art multi-party learning methods, as we demonstrated through simulations on real-world datasets.
Various convolutional neural network (CNN) based concepts have been introduced for the prostate's automatic segmentation and its coarse subdivision into transition zone (TZ) and peripheral zone (PZ). However, when targeting a fine-grained segmentation of TZ, PZ, distal prostatic urethra (DPU) and the anterior fibromuscular stroma (AFS), the task becomes more challenging and has not yet been solved at the level of human performance. One reason might be the insufficient amount of labeled data for supervised training. Therefore, we propose to apply a semi-supervised learning (SSL) technique named uncertainty-aware temporal self-learning (UATS) to overcome the expensive and time-consuming manual ground truth labeling. We combine the SSL techniques temporal ensembling and uncertainty-guided self-learning to benefit from unlabeled images, which are often readily available. Our method significantly outperforms the supervised baseline and obtained a Dice coefficient (DC) of up to 78.9% , 87.3%, 75.3%, 50.6% for TZ, PZ, DPU and AFS, respectively. The obtained results are in the range of human inter-rater performance for all structures. Moreover, we investigate the method's robustness against noise and demonstrate the generalization capability for varying ratios of labeled data and on other challenging tasks, namely the hippocampus and skin lesion segmentation. UATS achieved superiority segmentation quality compared to the supervised baseline, particularly for minimal amounts of labeled data.
Artificial neural network modeling does not need to consider the mechanism. It can map the implicit relationship between input and output and predict the performance of the system well. At the same time, it has the advantages of self-learning ability and high fault tolerance. The gas-liquid two phases in the rectification tower conduct interphase heat and mass transfer through countercurrent contact. The functional relationship between the product concentration at the top and bottom of the tower and the process parameters is extremely complex. The functional relationship can be accurately controlled by artificial neural network algorithms. The key components of the propylene distillation tower are the propane concentration at the top of the tower and the propylene concentration at the bottom of the tower. Accurate measurement of them plays a key role in increasing propylene yield in ethylene production enterprises. This article mainly introduces the neural network model and its application in the propylene distillation tower.
Despite the widespread utilization of deep neural networks (DNNs) for speech emotion recognition (SER), they are severely restricted due to the paucity of labeled data for training. Recently, segment-based approaches for SER have been evolving, which train backbone networks on shorter segments instead of whole utterances, and thus naturally augments training examples without additional resources. However, one core challenge remains for segment-based approaches: most emotional corpora do not provide ground-truth labels at the segment level. To supervisely train a segment-based emotion model on such datasets, the most common way assigns each segment the corresponding utterance's emotion label. However, this practice typically introduces noisy (incorrect) labels as emotional information is not uniformly distributed across the whole utterance. On the other hand, DNNs have been shown to easily over-fit a dataset when being trained with noisy labels. To this end, this work proposes a simple and effective deep self-learning (DSL) framework, which comprises a procedure to progressively correct segment-level labels in an iterative learning manner. The DSL method produces dynamically-generated and soft emotion labels, leading to significant performance improvements. Experiments on three well-known emotional corpora demonstrate noticeable gains using the proposed method.
General game testing relies on the use of human play testers, play test scripting, and prior knowledge of areas of interest to produce relevant test data. Using deep reinforcement learning (DRL), we introduce a self-learning mechanism to the game testing framework. With DRL, the framework is capable of exploring and/or exploiting the game mechanics based on a user-defined, reinforcing reward signal. As a result, test coverage is increased and unintended game play mechanics, exploits and bugs are discovered in a multitude of game types. In this paper, we show that DRL can be used to increase test coverage, find exploits, test map difficulty, and to detect common problems that arise in the testing of first-person shooter (FPS) games.
This paper represents a novel online self-learning disturbance observer (SLDO) by benefiting from the combination of a type-2 neuro-fuzzy structure (T2NFS), feedback-error learning scheme and sliding mode control (SMC) theory. The SLDO is developed within a framework of feedback-error learning scheme in which a conventional estimation law and a T2NFS work in parallel. In this scheme, the latter learns uncertainties and becomes the leading estimator whereas the former provides the learning error to the T2NFS for learning system dynamics. A learning algorithm established on SMC theory is derived for an interval type-2 fuzzy logic system. In addition to the stability of the learning algorithm, the stability of the SLDO and the stability of the overall system are proven in the presence of time-varying disturbances. Thanks to learning process by the T2NFS, the simulation results show that the SLDO is able to estimate time-varying disturbances precisely as distinct from the basic nonlinear disturbance observer (BNDO) so that the controller based on the SLDO ensures robust control performance for systems with time-varying uncertainties, and maintains nominal performance in the absence of uncertainties.
This paper focuses on a novel feedback linearization control (FLC) law based on a self-learning disturbance observer (SLDO) to counteract mismatched uncertainties. The FLC based on BNDO (FLC-BNDO) demonstrates robust control performance only against mismatched time-invariant uncertainties while the FLC based on SLDO (FLC-SLDO) demonstrates robust control performance against mismatched time-invariant and -varying uncertainties, and both of them maintain the nominal control performance in the absence of mismatched uncertainties. In the estimation scheme for the SLDO, the BNDO is used to provide a conventional estimation law, which is used as being the learning error for the type-2 neuro-fuzzy system (T2NFS), and T2NFS learns mismatched uncertainties. Thus, the T2NFS takes the overall control of the estimation signal entirely in a very short time and gives unbiased estimation results for the disturbance. A novel learning algorithm established on sliding mode control theory is derived for an interval type-2 fuzzy logic system. The stability of the overall system is proven for a second-order nonlinear system with mismatched uncertainties. The simulation results show that the FLC-SLDO demonstrates better control performance than the traditional FLC, FLC with an integral action (FLC-I) and FLC-BNDO.
This paper presents a novel Sliding Mode Control (SMC) algorithm to handle mismatched uncertainties in systems via a novel Self-Learning Disturbance Observer (SLDO). A computationally efficient SLDO is developed within a framework of feedback-error learning scheme in which a conventional estimation law and a Neuro-Fuzzy Structure (NFS) work in parallel. In this framework, the NFS estimates the mismatched disturbances and becomes the leading disturbance estimator while the former feeds the learning error to the NFS to learn system behavior. The simulation results demonstrate that the proposed SMC based on SLDO (SMC-SLDO) ensures the robust control performance in the presence of mismatched time-varying uncertainties when compared to SMC, integral SMC (ISMC) and SMC based on a Basic Nonlinear Disturbance Observer (SMC-BNDO), and also remains the nominal control performance in the absence of mismatched uncertainties. Additionally, the SMC-SLDO not only counteracts mismatched time-varying uncertainties but also improve the transient response performance in the presence of mismatched time-invariant uncertainties. Moreover, the controller gain of the SMC-SLDO is required to be selected larger than the upper bound of the disturbance estimation error rather than the upper bound of the actual disturbance to guarantee the system stability which results in eliminating the chattering effects on the control signal.
Recent research has shown that non-additive image steganographic frameworks effectively improve security performance through adjusting distortion distribution. However, as far as we know, all of the existing non-additive proposals are based on handcrafted policies, and can only be applied to a specific image domain, which heavily prevent non-additive steganography from releasing its full potentiality. In this paper, we propose an automatic non-additive steganographic distortion learning framework called MCTSteg to remove the above restrictions. Guided by the reinforcement learning paradigm, we combine Monte Carlo Tree Search (MCTS) and steganalyzer-based environmental model to build MCTSteg. MCTS makes sequential decisions to adjust distortion distribution without human intervention. Our proposed environmental model is used to obtain feedbacks from each decision. Due to its self-learning characteristic and domain-independent reward function, MCTSteg has become the first reported universal non-additive steganographic framework which can work in both spatial and JPEG domains. Extensive experimental results show that MCTSteg can effectively withstand the detection of both hand-crafted feature-based and deep-learning-based steganalyzers. In both spatial and JPEG domains, the security performance of MCTSteg steadily outperforms the state of the art by a clear margin under different scenarios.
Many neuroscientific applications require robust and accurate localization of neurons. It is still an unsolved problem because of the enormous variation in intensity, texture, spatial overlap, morphology and background artifacts. In addition, curation of a large dataset containing complete manual annotation of neurons from high-resolution images to train a classifier requires significant time and effort. We present Cellcounter, a deep learning-based model trained on images containing incompletely-annotated neurons with highly-varied morphology and control images containing artifacts and background structures. Leveraging the striking self-learning ability, Cellcounter gradually labels neurons, obviating the need for time-intensive complete annotation. Cellcounter shows its efficacy over the state of the arts in the accurate localization of neurons while significantly reducing false-positive detection in several protocols.
Unknown examples that are unseen during training often appear in real-world machine learning tasks, and an intelligent self-learning system should be able to distinguish between known and unknown examples. Accordingly, open set recognition (OSR), which addresses the problem of classifying knowns and identifying unknowns, has recently been highlighted. However, conventional deep neural networks using a softmax layer are vulnerable to overgeneralization, producing high confidence scores for unknowns. In this paper, we propose a simple OSR method based on the intuition that OSR performance can be maximized by setting strict and sophisticated decision boundaries that reject unknowns while maintaining satisfactory classification performance on knowns. For this purpose, a novel network structure is proposed, in which multiple one-vs-rest networks (OVRNs) follow a convolutional neural network feature extractor. Here, the OVRN is a simple feed-forward neural network that enhances the ability to reject nonmatches by learning class-specific discriminative features. Furthermore, the collective decision score is modeled by combining the multiple decisions reached by the OVRNs to alleviate overgeneralization. Extensive experiments were conducted on various datasets, and the experimental results showed that the proposed method performed significantly better than the state-of-the-art methods by effectively reducing overgeneralization.
Neural Machine Translation (NMT) approaches employing monolingual data are showing steady improvements in resource rich conditions. However, evaluations using real-world low-resource languages still result in unsatisfactory performance. This work proposes a novel zero-shot NMT modeling approach that learns without the now-standard assumption of a pivot language sharing parallel data with the zero-shot source and target languages. Our approach is based on three stages: initialization from any pre-trained NMT model observing at least the target language, augmentation of source sides leveraging target monolingual data, and learning to optimize the initial model to the zero-shot pair, where the latter two constitute a self-learning cycle. Empirical findings involving four diverse (in terms of a language family, script and relatedness) zero-shot pairs show the effectiveness of our approach with up to +5.93 BLEU improvement against a supervised bilingual baseline. Compared to unsupervised NMT, consistent improvements are observed even in a domain-mismatch setting, attesting to the usability of our method.
A physical self-learning machine can be defined as a nonlinear dynamical system that can be trained on data (similar to artificial neural networks), but where the update of the internal degrees of freedom that serve as learnable parameters happens autonomously. In this way, neither external processing and feedback nor knowledge of (and control of) these internal degrees of freedom is required. We introduce a general scheme for self-learning in any time-reversible Hamiltonian system. We illustrate the training of such a self-learning machine numerically for the case of coupled nonlinear wave fields.
Single image super-resolution (SISR), which aims to reconstruct a high-resolution (HR) image from a low-resolution (LR) observation, has been an active research topic in the area of image processing in recent decades. Particularly, deep learning-based super-resolution (SR) approaches have drawn much attention and have greatly improved the reconstruction performance on synthetic data. Recent studies show that simulation results on synthetic data usually overestimate the capacity to super-resolve real-world images. In this context, more and more researchers devote themselves to develop SR approaches for realistic images. This article aims to make a comprehensive review on real-world single image super-resolution (RSISR). More specifically, this review covers the critical publically available datasets and assessment metrics for RSISR, and four major categories of RSISR methods, namely the degradation modeling-based RSISR, image pairs-based RSISR, domain translation-based RSISR, and self-learning-based RSISR. Comparisons are also made among representative RSISR methods on benchmark datasets, in terms of both reconstruction quality and computational efficiency. Besides, we discuss challenges and promising research topics on RSISR.
Reinforcement learning (RL) is one of the most active fields of AI research. Despite the interest demonstrated by the research community in reinforcement learning, the development methodology still lags behind, with a severe lack of standard APIs to foster the development of RL applications. OpenAI Gym is probably the most used environment to develop RL applications and simulations, but most of the abstractions proposed in such a framework are still assuming a semi-structured methodology. This is particularly relevant for agent-based models whose purpose is to analyse adaptive behaviour displayed by self-learning agents in the simulation. In order to bridge this gap, we present a workflow and tools for the decoupled development and maintenance of multi-purpose agent-based models and derived single-purpose reinforcement learning environments, enabling the researcher to swap out environments with ones representing different perspectives or different reward models, all while keeping the underlying domain model intact and separate. The Sim-Env Python library generates OpenAI-Gym-compatible reinforcement learning environments that use existing or purposely created domain models as their simulation back-ends. Its design emphasizes ease-of-use, modularity and code separation.
Dense retrieval requires high-quality text sequence embeddings to support effective search in the representation space. Autoencoder-based language models are appealing in dense retrieval as they train the encoder to output high-quality embedding that can reconstruct the input texts. However, in this paper, we provide theoretical analyses and show empirically that an autoencoder language model with a low reconstruction loss may not provide good sequence representations because the decoder may take shortcuts by exploiting language patterns. To address this, we propose a new self-learning method that pre-trains the autoencoder using a \textit{weak} decoder, with restricted capacity and attention flexibility to push the encoder to provide better text representations. Our experiments on web search, news recommendation, and open domain question answering show that our pre-trained model significantly boosts the effectiveness and few-shot ability of dense retrieval models. Our code is available at https://github.com/microsoft/SEED-Encoder/.
The objective of this project is to solve one of the major problems faced by the people having word processing issues like trauma, or mild mental disability. "ARTH" is the short form of Algorithm for Reading Handily. ARTH is a self-learning set of algorithms that is an intelligent way of fulfilling the need for "reading and understanding the text effortlessly" which adjusts according to the needs of every user. The research project propagates in two steps. In the first step, the algorithm tries to identify the difficult words present in the text based on two features -- the number of syllables and usage frequency -- using a clustering algorithm. After the analysis of the clusters, the algorithm labels these clusters, according to their difficulty level. In the second step, the algorithm interacts with the user. It aims to test the user's comprehensibility of the text and his/her vocabulary level by taking an automatically generated quiz. The algorithm identifies the clusters which are difficult for the user, based on the result of the analysis. The meaning of perceived difficult words is displayed next to them. The technology "ARTH" focuses on the revival of the joy of reading among those people, who have a poor vocabulary or any word processing issues.
Knowledge distillation (KD), as an efficient and effective model compression technique, has been receiving considerable attention in deep learning. The key to its success is to transfer knowledge from a large teacher network to a small student one. However, most of the existing knowledge distillation methods consider only one type of knowledge learned from either instance features or instance relations via a specific distillation strategy in teacher-student learning. There are few works that explore the idea of transferring different types of knowledge with different distillation strategies in a unified framework. Moreover, the frequently used offline distillation suffers from a limited learning capacity due to the fixed teacher-student architecture. In this paper we propose a collaborative teacher-student learning via multiple knowledge transfer (CTSL-MKT) that prompts both self-learning and collaborative learning. It allows multiple students learn knowledge from both individual instances and instance relations in a collaborative way. While learning from themselves with self-distillation, they can also guide each other via online distillation. The experiments and ablation studies on four image datasets demonstrate that the proposed CTSL-MKT significantly outperforms the state-of-the-art KD methods.
Humanoid robots that act as human-robot interfaces equipped with social skills can assist people in many of their daily activities. Receptionist robots are one such application where social skills and appearance are of utmost importance. Many existing robot receptionist systems suffer from high cost and they do not disclose internal architectures for further development for robot researchers. Moreover, there does not exist customizable open-source robot receptionist frameworks to be deployed for any given application. In this paper we present an open-source robot receptionist intelligence core -- "DEVI"(means 'lady' in Sinhala), that provides researchers with ease of creating customized robot receptionists according to the requirements (cost, external appearance, and required processing power). Moreover, this paper also presents details on a prototype implementation of a physical robot using the DEVI system. The robot can give directional guidance with physical gestures, answer basic queries using a speech recognition and synthesis system, recognize and greet known people using face recognition and register new people in its database, using a self-learning neural network. Experiments conducted with DEVI show the effectiveness of the proposed system.