Recent advances in event-based neuromorphic systems have resulted in significant interest in the use and development of spiking neural networks (SNNs). However, the non-differentiable nature of spiking neurons makes SNNs incompatible with conventional backpropagation techniques. In spite of the significant progress made in training conventional deep neural networks (DNNs), training methods for SNNs still remain relatively poorly understood. In this paper, we present a novel framework for training recurrent SNNs. Analogous to the benefits presented by recurrent neural networks (RNNs) in learning time series models within DNNs, we develop SNNs based on long short-term memory (LSTM) networks. We show that LSTM spiking networks learn the timing of the spikes and temporal dependencies. We also develop a methodology for error backpropagation within LSTM-based SNNs. The developed architecture and method for backpropagation within LSTM-based SNNs enable them to learn long-term dependencies with comparable results to conventional LSTMs.
We prove local convergence of several notable gradient descentalgorithms used inmachine learning, for which standard stochastic gradient descent theorydoes not apply. This includes, first, online algorithms for recurrent models and dynamicalsystems, such as \emph{Real-time recurrent learning} (RTRL) and its computationally lighter approximations NoBackTrack and UORO; second,several adaptive algorithms such as RMSProp, online natural gradient, and Adam with $\beta^2\to 1$.Despite local convergence being a relatively weak requirement for a newoptimization algorithm, no local analysis was available for these algorithms, as far aswe knew. Analysis of these algorithms does not immediately followfrom standard stochastic gradient (SGD) theory. In fact, Adam has been provedto lack local convergence in some simple situations. For recurrent models, online algorithms modify the parameterwhile the model is running, which further complicates the analysis withrespect to simple SGD.Local convergence for these various algorithms results from a single,more general set of assumptions, in the setup of learning dynamicalsystems online. Thus, these results can cover other variants ofthe algorithms considered.We adopt an ``ergodic'' rather than probabilistic viewpoint, working withempirical time averages instead of probability distributions. This ismore data-agnostic andcreates differences with respect to standard SGD theory,especially for the range of possible learning rates. For instance, withcycling or per-epoch reshuffling over a finite dataset instead of purei.i.d. sampling with replacement, empiricalaverages of gradients converge at rate $1/T$ insteadof $1/\sqrt{T}$ (cycling acts as a variance reduction method),theoretically allowingfor larger learning rates than in SGD.
This paper proposes a novel system to estimate and track the 3D poses of multiple persons in calibrated RGB-Depth camera networks. The multi-view 3D pose of each person is computed by a central node which receives the single-view outcomes from each camera of the network. Each single-view outcome is computed by using a CNN for 2D pose estimation and extending the resulting skeletons to 3D by means of the sensor depth. The proposed system is marker-less, multi-person, independent of background and does not make any assumption on people appearance and initial pose. The system provides real-time outcomes, thus being perfectly suited for applications requiring user interaction. Experimental results show the effectiveness of this work with respect to a baseline multi-view approach in different scenarios. To foster research and applications based on this work, we released the source code in OpenPTrack, an open source project for RGB-D people tracking.
Training a spoken language understanding system, as the one in Alexa, typically requires a large human-annotated corpus of data. Manual annotations are expensive and time consuming. In Alexa Skill Kit (ASK) user experience with the skill greatly depends on the amount of data provided by skill developer. In this work, we present an automatic natural language generation system, capable of generating both human-like interactions and annotations by the means of paraphrasing. Our approach consists of machine translation (MT) inspired encoder-decoder deep recurrent neural network. We evaluate our model on the impact it has on ASK skill, intent, named entity classification accuracy and sentence level coverage, all of which demonstrate significant improvements for unseen skills on natural language understanding (NLU) models, trained on the data augmented with paraphrases.
While the satellite-based Global Positioning System (GPS) is adequate for some outdoor applications, many other applications are held back by its multi-meter positioning errors and poor indoor coverage. In this paper, we study the feasibility of real-time video-based localization on resource-constrained platforms. Before commencing a localization task, a video-based localization system downloads an offline model of a restricted target environment, such as a set of city streets, or an indoor shopping mall. The system is then able to localize the user within the model, using only video as input. To enable such a system to run on resource-constrained embedded systems or smartphones, we (a) propose techniques for efficiently building a 3D model of a surveyed path, through frame selection and efficient feature matching, (b) substantially reduce model size by multiple compression techniques, without sacrificing localization accuracy, (c) propose efficient and concurrent techniques for feature extraction and matching to enable online localization, (d) propose a method with interleaved feature matching and optical flow based tracking to reduce the feature extraction and matching time in online localization. Based on an extensive set of both indoor and outdoor videos, manually annotated with location ground truth, we demonstrate that sub-meter accuracy, at real-time rates, is achievable on smart-phone type platforms, despite challenging video conditions.
The pandemic of COVID-19 has caused millions of infectious. Due to the false-negative rate and the time cost of conventional RT-PCR tests, X-ray images and Computed Tomography (CT) images based diagnosing become widely adopted. Therefore, researchers of the computer vision area have developed many automatic diagnosing models to help the radiologists and pro-mote the diagnosing accuracy. In this paper, we present a review of these recently emerging automatic diagnosing models. 62 models from 14, February to 5, May, 2020 are involved. We analyzed the models from the perspective of preprocessing, feature extraction, classification, and evaluation. Then we pointed out that domain adaption in transfer learning and interpretability promotion are the possible future directions.
This letter proposes a novel communication-efficient and privacy-preserving distributed machine learning framework, coined Mix2FLD. To address uplink-downlink capacity asymmetry, local model outputs are uploaded to a server in the uplink as in federated distillation (FD), whereas global model parameters are downloaded in the downlink as in federated learning (FL). This requires a model output-to-parameter conversion at the server, after collecting additional data samples from devices. To preserve privacy while not compromising accuracy, linearly mixed-up local samples are uploaded, and inversely mixed up across different devices at the server. Numerical evaluations show that Mix2FLD achieves up to 16.7% higher test accuracy while reducing convergence time by up to 18.8% under asymmetric uplink-downlink channels compared to FL.
The paper proposes the stable motion control law design method for non-honomic differential-drive mobile robot with system and measurement noise in discrete time domain. This method is performed basing on dividing operating configuration of robot into two parts: glocal and local configuration then the control law is designed following Lyapunov stable theory for two configuration. The proposed stable control laws is able to reach asymptotically stably to target position and orientation from any initial conditions even existing noise in the system. Some simulation results have demonstrated the effect of proposed method.
Self-supervised learning has made unsupervised pretraining relevant again for difficult computer vision tasks. The most effective self-supervised methods involve prediction tasks based on features extracted from diverse views of the data. DeepInfoMax (DIM) is a self-supervised method which leverages the internal structure of deep networks to construct such views, forming prediction tasks between local features which depend on small patches in an image and global features which depend on the whole image. In this paper, we extend DIM to the video domain by leveraging similar structure in spatio-temporal networks, producing a method we call Video Deep InfoMax(VDIM). We find that drawing views from both natural-rate sequences and temporally-downsampled sequences yields results on Kinetics-pretrained action recognition tasks which match or outperform prior state-of-the-art methods that use more costly large-time-scale transformer models. We also examine the effects of data augmentation and fine-tuning methods, accomplishingSoTA by a large margin when training only on the UCF-101 dataset.
Underwater marine inspections for ship hull or marine debris, etc. are one of the vital measures carried out to ensure the safety of marine structures and underwater species. This work details the design, development and qualification of a compact and economical observation class Remotely Operated Vehicle (ROV) prototype, intended for carrying out scientific research in shallow-waters. The ROV has a real-time processor and controller onboard, which synchronizes the movement of the vehicle based on the commands from the surface station. The vehicle piloting is done using the onboard Raspberry pi camera and the support of some navigation sensors like Global Positioning System (GPS), inertial, temperature, depth and pressure. This prototype of ROV is a compact unit built using a limited number of components and is suitable for underwater inspection using a single camera. The developed ROV is initially tested in a pool.