Paper Group ANR 914
300 GHz Radar Object Recognition based on Deep Neural Networks and Transfer Learning. Vision-Language Navigation with Self-Supervised Auxiliary Reasoning Tasks. Sample-Optimal Parametric Q-Learning Using Linearly Additive Features. Communication-Efficient Federated Deep Learning with Asynchronous Model Update and Temporally Weighted Aggregation. Co …
300 GHz Radar Object Recognition based on Deep Neural Networks and Transfer Learning
| Title | 300 GHz Radar Object Recognition based on Deep Neural Networks and Transfer Learning |
| Authors | Marcel Sheeny, Andrew Wallace, Sen Wang |
| Abstract | For high resolution scene mapping and object recognition, optical technologies such as cameras and LiDAR are the sensors of choice. However, for robust future vehicle autonomy and driver assistance in adverse weather conditions, improvements in automotive radar technology, and the development of algorithms and machine learning for robust mapping and recognition are essential. In this paper, we describe a methodology based on deep neural networks to recognise objects in 300GHz radar images, investigating robustness to changes in range, orientation and different receivers in a laboratory environment. As the training data is limited, we have also investigated the effects of transfer learning. As a necessary first step before road trials, we have also considered detection and classification in multiple object scenes. |
| Tasks | Object Recognition, Transfer Learning |
| Published | 2019-12-06 |
| URL | https://arxiv.org/abs/1912.03157v1 |
| https://arxiv.org/pdf/1912.03157v1.pdf | |
| PWC | https://paperswithcode.com/paper/300-ghz-radar-object-recognition-based-on |
| Repo | |
| Framework | |
Vision-Language Navigation with Self-Supervised Auxiliary Reasoning Tasks
| Title | Vision-Language Navigation with Self-Supervised Auxiliary Reasoning Tasks |
| Authors | Fengda Zhu, Yi Zhu, Xiaojun Chang, Xiaodan Liang |
| Abstract | Vision-Language Navigation (VLN) is a task where agents learn to navigate following natural language instructions. The key to this task is to perceive both the visual scene and natural language sequentially. Conventional approaches exploit the vision and language features in cross-modal grounding. However, the VLN task remains challenging, since previous works have neglected the rich semantic information contained in the environment (such as implicit navigation graphs or sub-trajectory semantics). In this paper, we introduce Auxiliary Reasoning Navigation (AuxRN), a framework with four self-supervised auxiliary reasoning tasks to take advantage of the additional training signals derived from the semantic information. The auxiliary tasks have four reasoning objectives: explaining the previous actions, estimating the navigation progress, predicting the next orientation, and evaluating the trajectory consistency. As a result, these additional training signals help the agent to acquire knowledge of semantic representations in order to reason about its activity and build a thorough perception of the environment. Our experiments indicate that auxiliary reasoning tasks improve both the performance of the main task and the model generalizability by a large margin. Empirically, we demonstrate that an agent trained with self-supervised auxiliary reasoning tasks substantially outperforms the previous state-of-the-art method, being the best existing approach on the standard benchmark. |
| Tasks | Vision-Language Navigation |
| Published | 2019-11-18 |
| URL | https://arxiv.org/abs/1911.07883v4 |
| https://arxiv.org/pdf/1911.07883v4.pdf | |
| PWC | https://paperswithcode.com/paper/vision-language-navigation-with-self |
| Repo | |
| Framework | |
Sample-Optimal Parametric Q-Learning Using Linearly Additive Features
| Title | Sample-Optimal Parametric Q-Learning Using Linearly Additive Features |
| Authors | Lin F. Yang, Mengdi Wang |
| Abstract | Consider a Markov decision process (MDP) that admits a set of state-action features, which can linearly express the process’s probabilistic transition model. We propose a parametric Q-learning algorithm that finds an approximate-optimal policy using a sample size proportional to the feature dimension $K$ and invariant with respect to the size of the state space. To further improve its sample efficiency, we exploit the monotonicity property and intrinsic noise structure of the Bellman operator, provided the existence of anchor state-actions that imply implicit non-negativity in the feature space. We augment the algorithm using techniques of variance reduction, monotonicity preservation, and confidence bounds. It is proved to find a policy which is $\epsilon$-optimal from any initial state with high probability using $\widetilde{O}(K/\epsilon^2(1-\gamma)^3)$ sample transitions for arbitrarily large-scale MDP with a discount factor $\gamma\in(0,1)$. A matching information-theoretical lower bound is proved, confirming the sample optimality of the proposed method with respect to all parameters (up to polylog factors). |
| Tasks | Q-Learning |
| Published | 2019-02-13 |
| URL | https://arxiv.org/abs/1902.04779v2 |
| https://arxiv.org/pdf/1902.04779v2.pdf | |
| PWC | https://paperswithcode.com/paper/sample-optimal-parametric-q-learning-with |
| Repo | |
| Framework | |
Communication-Efficient Federated Deep Learning with Asynchronous Model Update and Temporally Weighted Aggregation
| Title | Communication-Efficient Federated Deep Learning with Asynchronous Model Update and Temporally Weighted Aggregation |
| Authors | Yang Chen, Xiaoyan Sun, Yaochu Jin |
| Abstract | Federated learning obtains a central model on the server by aggregating models trained locally on clients. As a result, federated learning does not require clients to upload their data to the server, thereby preserving the data privacy of the clients. One challenge in federated learning is to reduce the client-server communication since the end devices typically have very limited communication bandwidth. This paper presents an enhanced federated learning technique by proposing a synchronous learning strategy on the clients and a temporally weighted aggregation of the local models on the server. In the asynchronous learning strategy, different layers of the deep neural networks are categorized into shallow and deeps layers and the parameters of the deep layers are updated less frequently than those of the shallow layers. Furthermore, a temporally weighted aggregation strategy is introduced on the server to make use of the previously trained local models, thereby enhancing the accuracy and convergence of the central model. The proposed algorithm is empirically on two datasets with different deep neural networks. Our results demonstrate that the proposed asynchronous federated deep learning outperforms the baseline algorithm both in terms of communication cost and model accuracy. |
| Tasks | |
| Published | 2019-03-18 |
| URL | http://arxiv.org/abs/1903.07424v1 |
| http://arxiv.org/pdf/1903.07424v1.pdf | |
| PWC | https://paperswithcode.com/paper/communication-efficient-federated-deep |
| Repo | |
| Framework | |
Computational Astrocyence: Astrocytes encode inhibitory activity into the frequency and spatial extent of their calcium elevations
| Title | Computational Astrocyence: Astrocytes encode inhibitory activity into the frequency and spatial extent of their calcium elevations |
| Authors | Ioannis E. Polykretis, Vladimir A. Ivanov, Konstantinos P. Michmizos |
| Abstract | Deciphering the complex interactions between neurotransmission and astrocytic $Ca^{2+}$ elevations is a target promising a comprehensive understanding of brain function. While the astrocytic response to excitatory synaptic activity has been extensively studied, how inhibitory activity results to intracellular $Ca^{2+}$ waves remains elusive. In this study, we developed a compartmental astrocytic model that exhibits distinct levels of responsiveness to inhibitory activity. Our model suggested that the astrocytic coverage of inhibitory terminals defines the spatial and temporal scale of their $Ca^{2+}$ elevations. Understanding the interplay between the synaptic pathways and the astrocytic responses will help us identify how astrocytes work independently and cooperatively with neurons, in health and disease. |
| Tasks | |
| Published | 2019-03-18 |
| URL | http://arxiv.org/abs/1903.07533v1 |
| http://arxiv.org/pdf/1903.07533v1.pdf | |
| PWC | https://paperswithcode.com/paper/computational-astrocyence-astrocytes-encode |
| Repo | |
| Framework | |
Synthetic vs Real: Deep Learning on Controlled Noise
| Title | Synthetic vs Real: Deep Learning on Controlled Noise |
| Authors | Lu Jiang, Di Huang, Weilong Yang |
| Abstract | Performing controlled experiments on noisy data is essential in thoroughly understanding deep learning across a spectrum of noise levels. Due to the lack of suitable datasets, previous research have only examined deep learning on controlled synthetic noise, and real-world noise has never been systematically studied in a controlled setting. To this end, this paper establishes a benchmark of real-world noisy labels at 10 controlled noise levels. As real-world noise possesses unique properties, to understand the difference, we conduct a large-scale study across a variety of noise levels and types, architectures, methods, and training settings. Our study shows that: (1) Deep Neural Networks (DNNs) generalize much better on real-world noise. (2) DNNs may not learn patterns first on real-world noisy data. (3) When networks are fine-tuned, ImageNet architectures generalize well on noisy data. (4) Real-world noise appears to be less harmful, yet it is more difficult for robust DNN methods to improve. (5) Robust learning methods that work well on synthetic noise may not work as well on real-world noise, and vice versa. We hope our benchmark, as well as our findings, will facilitate deep learning research on noisy data. |
| Tasks | |
| Published | 2019-11-21 |
| URL | https://arxiv.org/abs/1911.09781v1 |
| https://arxiv.org/pdf/1911.09781v1.pdf | |
| PWC | https://paperswithcode.com/paper/synthetic-vs-real-deep-learning-on-controlled-1 |
| Repo | |
| Framework | |
The Quantum Version Of Classification Decision Tree Constructing Algorithm C5.0
| Title | The Quantum Version Of Classification Decision Tree Constructing Algorithm C5.0 |
| Authors | Kamil Khadiev, Ilnaz Mannapov, Liliya Safina |
| Abstract | In the paper, we focus on complexity of C5.0 algorithm for constructing decision tree classifier that is the models for the classification problem from machine learning. In classical case the decision tree is constructed in $O(hd(NM+N \log N))$ running time, where $M$ is a number of classes, $N$ is the size of a training data set, $d$ is a number of attributes of each element, $h$ is a tree height. Firstly, we improved the classical version, the running time of the new version is $O(h\cdot d\cdot N\log N)$. Secondly, we suggest a quantum version of this algorithm, which uses quantum subroutines like the amplitude amplification and the D{"u}rr-H{\o}yer minimum search algorithms that are based on Grover’s algorithm. The running time of the quantum algorithm is $O\big(h\cdot \sqrt{d}\log d \cdot N \log N\big)$ that is better than complexity of the classical algorithm. |
| Tasks | |
| Published | 2019-07-16 |
| URL | https://arxiv.org/abs/1907.06840v1 |
| https://arxiv.org/pdf/1907.06840v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-quantum-version-of-classification |
| Repo | |
| Framework | |
IMPACT: Importance Weighted Asynchronous Architectures with Clipped Target Networks
| Title | IMPACT: Importance Weighted Asynchronous Architectures with Clipped Target Networks |
| Authors | Michael Luo, Jiahao Yao, Richard Liaw, Eric Liang, Ion Stoica |
| Abstract | The practical usage of reinforcement learning agents is often bottlenecked by the duration of training time. To accelerate training, practitioners often turn to distributed reinforcement learning architectures to parallelize and accelerate the training process. However, modern methods for scalable reinforcement learning (RL) often tradeoff between the throughput of samples that an RL agent can learn from (sample throughput) and the quality of learning from each sample (sample efficiency). In these scalable RL architectures, as one increases sample throughput (i.e. increasing parallelization in IMPALA), sample efficiency drops significantly. To address this, we propose a new distributed reinforcement learning algorithm, IMPACT. IMPACT extends IMPALA with three changes: a target network for stabilizing the surrogate objective, a circular buffer, and truncated importance sampling. In discrete action-space environments, we show that IMPACT attains higher reward and, simultaneously, achieves up to 30% decrease in training wall-time than that of IMPALA. For continuous control environments, IMPACT trains faster than existing scalable agents while preserving the sample efficiency of synchronous PPO. |
| Tasks | Continuous Control |
| Published | 2019-11-30 |
| URL | https://arxiv.org/abs/1912.00167v3 |
| https://arxiv.org/pdf/1912.00167v3.pdf | |
| PWC | https://paperswithcode.com/paper/impact-importance-weighted-asynchronous-1 |
| Repo | |
| Framework | |
Visual and Semantic Prototypes-Jointly Guided CNN for Generalized Zero-shot Learning
| Title | Visual and Semantic Prototypes-Jointly Guided CNN for Generalized Zero-shot Learning |
| Authors | Chuanxing Geng, Lue Tao, Songcan Chen |
| Abstract | In the process of exploring the world, the curiosity constantly drives humans to cognize new things. Supposing you are a zoologist, for a presented animal image, you can recognize it immediately if you know its class. Otherwise, you would more likely attempt to cognize it by exploiting the side-information (e.g., semantic information, etc.) you have accumulated. Inspired by this, this paper decomposes the generalized zero-shot learning (G-ZSL) task into an open set recognition (OSR) task and a zero-shot learning (ZSL) task, where OSR recognizes seen classes (if we have seen (or known) them) and rejects unseen classes (if we have never seen (or known) them before), while ZSL identifies the unseen classes rejected by the former. Simultaneously, without violating OSR’s assumptions (only known class knowledge is available in training), we also first attempt to explore a new generalized open set recognition (G-OSR) by introducing the accumulated side-information from known classes to OSR. For G-ZSL, such a decomposition effectively solves the class overfitting problem with easily misclassifying unseen classes as seen classes. The problem is ubiquitous in most existing G-ZSL methods. On the other hand, for G-OSR, introducing such semantic information of known classes not only improves the recognition performance but also endows OSR with the cognitive ability of unknown classes. Specifically, a visual and semantic prototypes-jointly guided convolutional neural network (VSG-CNN) is proposed to fulfill these two tasks (G-ZSL and G-OSR) in a unified end-to-end learning framework. Extensive experiments on benchmark datasets demonstrate the advantages of our learning framework. |
| Tasks | Open Set Learning, Zero-Shot Learning |
| Published | 2019-08-12 |
| URL | https://arxiv.org/abs/1908.03983v2 |
| https://arxiv.org/pdf/1908.03983v2.pdf | |
| PWC | https://paperswithcode.com/paper/visual-and-semantic-prototypes-jointly-guided |
| Repo | |
| Framework | |
BatVision: Learning to See 3D Spatial Layout with Two Ears
| Title | BatVision: Learning to See 3D Spatial Layout with Two Ears |
| Authors | Jesper Haahr Christensen, Sascha Hornauer, Stella Yu |
| Abstract | Many species have evolved advanced non-visual perception while artificial systems fall behind. Radar and ultrasound complement camera-based vision but they are often too costly and complex to set up for very limited information gain. In nature, sound is used effectively by bats, dolphins, whales, and humans for navigation and communication. However, it is unclear how to best harness sound for machine perception. Inspired by bats’ echolocation mechanism, we design a low-cost BatVision system that is capable of seeing the 3D spatial layout of space ahead by just listening with two ears. Our system emits short chirps from a speaker and records returning echoes through microphones in an artificial human pinnae pair. During training, we additionally use a stereo camera to capture color images for calculating scene depths. We train a model to predict depth maps and even grayscale images from the sound alone. During testing, our trained BatVision provides surprisingly good predictions of 2D visual scenes from two 1D audio signals. Such a sound to vision system would benefit robot navigation and machine vision, especially in low-light or no-light conditions. Our code and data are publicly available. |
| Tasks | Robot Navigation |
| Published | 2019-12-15 |
| URL | https://arxiv.org/abs/1912.07011v3 |
| https://arxiv.org/pdf/1912.07011v3.pdf | |
| PWC | https://paperswithcode.com/paper/batvision-learning-to-see-3d-spatial-layout |
| Repo | |
| Framework | |
Biologically inspired sleep algorithm for artificial neural networks
| Title | Biologically inspired sleep algorithm for artificial neural networks |
| Authors | Giri P Krishnan, Timothy Tadros, Ramyaa Ramyaa, Maxim Bazhenov |
| Abstract | Sleep plays an important role in incremental learning and consolidation of memories in biological systems. Motivated by the processes that are known to be involved in sleep generation in biological networks, we developed an algorithm that implements a sleep-like phase in artificial neural networks (ANNs). After initial training phase, we convert the ANN to a spiking neural network (SNN) and simulate an offline sleep-like phase using spike-timing dependent plasticity rules to modify synaptic weights. The SNN is then converted back to the ANN and evaluated or trained on new inputs. We demonstrate several performance improvements after applying this processing to ANNs trained on MNIST, CUB200 and a motivating toy dataset. First, in an incremental learning framework, sleep is able to recover older tasks that were otherwise forgotten in the ANN without sleep phase due to catastrophic forgetting. Second, sleep results in forward transfer learning of unseen tasks. Finally, sleep improves generalization ability of the ANNs to classify images with various types of noise. We provide a theoretical basis for the beneficial role of the brain-inspired sleep-like phase for the ANNs and present an algorithmic way for future implementations of the various features of sleep in deep learning ANNs. Overall, these results suggest that biological sleep can help mitigate a number of problems ANNs suffer from, such as poor generalization and catastrophic forgetting for incremental learning. |
| Tasks | Transfer Learning |
| Published | 2019-08-01 |
| URL | https://arxiv.org/abs/1908.02240v1 |
| https://arxiv.org/pdf/1908.02240v1.pdf | |
| PWC | https://paperswithcode.com/paper/biologically-inspired-sleep-algorithm-for |
| Repo | |
| Framework | |
Multi-Agent Thompson Sampling for Bandit Applications with Sparse Neighbourhood Structures
| Title | Multi-Agent Thompson Sampling for Bandit Applications with Sparse Neighbourhood Structures |
| Authors | Timothy Verstraeten, Eugenio Bargiacchi, Pieter JK Libin, Jan Helsen, Diederik M Roijers, Ann Nowé |
| Abstract | Multi-agent coordination is prevalent in many real-world applications. However, such coordination is challenging due to its combinatorial nature. An important observation in this regard is that agents in the real world often only directly affect a limited set of neighbouring agents. Leveraging such loose couplings among agents is key to making coordination in multi-agent systems feasible. In this work, we focus on learning to coordinate. Specifically, we consider the multi-agent multi-armed bandit framework, in which fully cooperative loosely-coupled agents must learn to coordinate their decisions to optimize a common objective. We propose multi-agent Thompson sampling (MATS), a new Bayesian exploration-exploitation algorithm that leverages loose couplings. We provide a regret bound that is sublinear in time and low-order polynomial in the highest number of actions of a single agent for sparse coordination graphs. Additionally, we empirically show that MATS outperforms the state-of-the-art algorithm, MAUCE, on two synthetic benchmarks, and a novel benchmark with Poisson distributions. An example of a loosely-coupled multi-agent system is a wind farm. Coordination within the wind farm is necessary to maximize power production. As upstream wind turbines only affect nearby downstream turbines, we can use MATS to efficiently learn the optimal control mechanism for the farm. To demonstrate the benefits of our method toward applications we apply MATS to a realistic wind farm control task. In this task, wind turbines must coordinate their alignments with respect to the incoming wind vector in order to optimize power production. Our results show that MATS improves significantly upon state-of-the-art coordination methods in terms of performance, demonstrating the value of using MATS in practical applications with sparse neighbourhood structures. |
| Tasks | |
| Published | 2019-11-22 |
| URL | https://arxiv.org/abs/1911.10120v2 |
| https://arxiv.org/pdf/1911.10120v2.pdf | |
| PWC | https://paperswithcode.com/paper/thompson-sampling-for-factored-multi-agent |
| Repo | |
| Framework | |
Efficient Implementation of Second-Order Stochastic Approximation Algorithms in High-Dimensional Problems
| Title | Efficient Implementation of Second-Order Stochastic Approximation Algorithms in High-Dimensional Problems |
| Authors | Jingyi Zhu, Long Wang, James C. Spall |
| Abstract | Stochastic approximation (SA) algorithms have been widely applied in minimization problems when the loss functions and/or the gradient information are only accessible through noisy evaluations. Stochastic gradient (SG) descent—a first-order algorithm and a workhorse of much machine learning—is perhaps the most famous form of SA. Among all SA algorithms, the second-order simultaneous perturbation stochastic approximation (2SPSA) and the second-order stochastic gradient (2SG) are particularly efficient in handling high-dimensional problems, covering both gradient-free and gradient-based scenarios. However, due to the necessary matrix operations, the per-iteration floating-point-operations (FLOPs) cost of the standard 2SPSA/2SG is $O(p^3)$, where $p$ is the dimension of the underlying parameter. Note that the $O(p^3)$ FLOPs cost is distinct from the classical SPSA-based per-iteration $O(1)$ cost in terms of the number of noisy function evaluations. In this work, we propose a technique to efficiently implement the 2SPSA/2SG algorithms via the symmetric indefinite matrix factorization and show that the FLOPs cost is reduced from $O(p^3)$ to $O(p^2)$. The formal almost sure convergence and rate of convergence for the newly proposed approach are directly inherited from the standard 2SPSA/2SG. The improvement in efficiency and numerical stability is demonstrated in two numerical studies. |
| Tasks | |
| Published | 2019-06-23 |
| URL | https://arxiv.org/abs/1906.09533v2 |
| https://arxiv.org/pdf/1906.09533v2.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-implementation-of-second-order |
| Repo | |
| Framework | |
Design and Implementation of Linked Planning Domain Definition Language
| Title | Design and Implementation of Linked Planning Domain Definition Language |
| Authors | Michiaki Tatsubori, Asim Munawar, Takao Moriyama |
| Abstract | Planning is a critical component of any artificial intelligence system that concerns the realization of strategies or action sequences typically for intelligent agents and autonomous robots. Given predefined parameterized actions, a planning service should accept a query with the goal and initial state to give a solution with a sequence of actions applied to environmental objects. This paper addresses the problem by providing a repository of actions generically applicable to various environmental objects based on Semantic Web technologies. Ontologies are used for asserting constraints in common sense as well as for resolving compatibilities between actions and states. Constraints are defined using Web standards such as SPARQL and SHACL to allow conditional predicates. We demonstrate the usefulness of the proposed planning domain description language with our robotics applications. |
| Tasks | Common Sense Reasoning |
| Published | 2019-12-17 |
| URL | https://arxiv.org/abs/1912.07834v1 |
| https://arxiv.org/pdf/1912.07834v1.pdf | |
| PWC | https://paperswithcode.com/paper/design-and-implementation-of-linked-planning |
| Repo | |
| Framework | |
Deep Unsupervised Clustering with Clustered Generator Model
| Title | Deep Unsupervised Clustering with Clustered Generator Model |
| Authors | Dandan Zhu, Tian Han, Linqi Zhou, Xiaokang Yang, Ying Nian Wu |
| Abstract | This paper addresses the problem of unsupervised clustering which remains one of the most fundamental challenges in machine learning and artificial intelligence. We propose the clustered generator model for clustering which contains both continuous and discrete latent variables. Discrete latent variables model the cluster label while the continuous ones model variations within each cluster. The learning of the model proceeds in a unified probabilistic framework and incorporates the unsupervised clustering as an inner step without the need for an extra inference model as in existing variational-based models. The latent variables learned serve as both observed data embedding or latent representation for data distribution. Our experiments show that the proposed model can achieve competitive unsupervised clustering accuracy and can learn disentangled latent representations to generate realistic samples. In addition, the model can be naturally extended to per-pixel unsupervised clustering which remains largely unexplored. |
| Tasks | |
| Published | 2019-11-19 |
| URL | https://arxiv.org/abs/1911.08459v1 |
| https://arxiv.org/pdf/1911.08459v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-unsupervised-clustering-with-clustered |
| Repo | |
| Framework | |
