FE - DI | Documentos por Auto-Depósito
Permanent URI for this collection
Browse
Browsing FE - DI | Documentos por Auto-Depósito by Author "Alexandre, Luís"
Now showing 1 - 10 of 25
Results Per Page
Sort Options
- An Overview of Blockchain Integration with Robotics and Artificial IntelligencePublication . Lopes, Vasco; Alexandre, LuísBlockchain technology is growing everyday at a fast-passed rhythm and it's possible to integrate it with many systems, namely Robotics with AI services. However, this is still a recent field and there isn't yet a clear understanding of what it could potentially become. In this paper, we conduct an overview of many different methods and platforms that try to leverage the power of blockchain into robotic systems, to improve AI services or to solve problems that are present in the major blockchains, which can lead to the ability of creating robotic systems with increased capabilities and security. We present an overview, discuss the methods and conclude the paper with our view on the future of the integration of these technologies.
- An Overview of Blockchain Integration with Robotics and Artificial IntelligencePublication . Lopes, Vasco; Alexandre, LuísBlockchain technology is growing everyday at a fast-passed rhythm and it is possible to integrate it with many systems, namely Robotics with AI services. However, this is still a recent field and there is not yet a clear understanding of what it could potentially become. In this paper, we conduct an overview of many different methods and platforms that try to leverage the power of blockchain into robotic systems, to improve AI services, or to solve problems that are present in the major blockchains, which can lead to the ability of creating robotic systems with increased capabilities and security. We present an overview, discuss the methods, and conclude the paper with our view on the future of the integration of these technologies.
- Application of Lifelong Learning with CNNs to Visual Robotic Classification TasksPublication . Zacarias, Abel; Alexandre, LuísThe field of robotics is becoming continuously more important, due to the impact it can bring to our everyday life. A long standing problem with neural network learning is the catastrophic forgetting when one tries to use the same network to learn more than one task. In this paper we present results of the application of a method to avoid catastrophic forgetting while using Convolutional Neural Networks (CNNs) to some visual recognition tasks relevant to the field of robotics. The results show that with this method a robot can learn new tasks without forgetting the previous learned tasks. Results also showed that if we applied this method, the performance on isolated tasks increases and it is better to use it than train a CNN in an isolated way (single task). We use for our experiments two well known data sets, namely, Olivetti Faces and Fashion-MNIST.
- Controlling Robots using Artificial Intelligence and a Consortium BlockchainPublication . Lopes, Vasco; Alexandre, Luís; Pereira, NunoBlockchain is a disruptive technology that is normally used within financial applications, however it can be very beneficial also in certain robotic contexts, such as when an immutable register of events is required. Among the several properties of Blockchain that can be useful within robotic environments, we find not just immutability but also decentralization of the data, irreversibility, accessibility and non-repudiation. In this paper, we propose an architecture that uses blockchain as a ledger and smart-contract technology for robotic control by using external parties, Oracles, to process data. We show how to register events in a secure way, how it is possible to use smart-contracts to control robots and how to interface with external Artificial Intelligence algorithms for image analysis. The proposed architecture is modular and can be used in multiple contexts such as in manufacturing, network control, robot control, and others, since it is easy to integrate, adapt, maintain and extend to new domains.
- Detecting Robotic Anomalies using RobotChainPublication . Lopes, Vasco; Alexandre, LuísRobotic events can provide notable amounts of information regarding a robot’s status, which can be extrapolated to detect productivity, anomalies, malfunctions and used for monitorization. However, when problems occur in sensitive environments like a factory, the logs of a machine may be discarded because they are susceptible to chances and malicious intents. In this paper we propose to use RobotChain for anomaly detection. RobotChain is a method to securely register robotic events, using a blockchain, which ensures that once an event gets registered on it, it’s secured and cannot be tampered with. We show how this system can be leveraged with the module for anomaly detection, that uses the information contained on the blockchain to detect anomalies on a UR3 robot.
- Distributed Learning of CNNs on Heterogeneous CPU/GPU ArchitecturesPublication . Marques, José; Falcao, Gabriel; Alexandre, LuísConvolutional Neural Networks (CNNs) have shown to be powerful classi cation tools in tasks that range from check reading to medical diagnosis, reaching close to human perception, and in some cases surpassing it. However, the problems to solve are becoming larger and more complex, which translates to larger CNNs, leading to longer training times|the computational complex part|that not even the adoption of Graphics Processing Units (GPUs) could keep up to. This problem is partially solved by using more processing units and distributed training methods that are o ered by several frameworks dedicated to neural network training, such as Ca e, Torch or TensorFlow. However, these techniques do not take full advantage of the possible parallelization o ered by CNNs and the cooperative use of heterogeneous devices with di erent processing capabilities, clock speeds, memory size, among others. This paper presents a new method for the parallel training of CNNs that can be considered as a particular instantiation of model parallelism, where only the convolutional layer is distributed. In fact, the convolutions processed during training (forward and backward propagation included) represent from 60-90% of global processing time. The paper analyzes the in uence of network size, bandwidth, batch size, number of devices, including their processing capabilities, and other parameters. Results show that this technique is capable of diminishing the training time without a ecting the classi cation performance for both CPUs and GPUs. For the CIFAR-10 dataset, using a CNN with two convolutional layers, and 500 and 1500 kernels, respectively, best speedups achieve 3:28 using four CPUs and 2:45 with three GPUs. Modern imaging datasets, larger and more complex than CIFAR-10 will certainly require more than 60-90% of processing time calculating convolutions, and speedups will tend to increase accordingly.
- Distribution-Based Categorization of Classifier Transfer LearningPublication . Sousa, Ricardo Gamelas; Alexandre, Luís; Santos, Jorge M.; Silva, Luís M.; Sá, Joaquim Marques deTransfer Learning (TL) aims to transfer knowledge acquired in one problem, the source problem, onto another problem, the target problem, dispensing with the bottom-up construction of the target model. Due to its relevance, TL has gained significant interest in the Machine Learning community since it paves the way to devise intelligent learning models that can easily be tailored to many different applications. As it is natural in a fast evolving area, a wide variety of TL methods, settings and nomenclature have been proposed so far. However, a wide range of works have been reporting different names for the same concepts. This concept and terminology mixture contribute however to obscure the TL field, hindering its proper consideration. In this paper we present a review of the literature on the majority of classification TL methods, and also a distribution-based categorization of TL with a common nomenclature suitable to classification problems. Under this perspective three main TL categories are presented, discussed and illustrated with examples.
- Image Normalization Influence in Mammographic Classification with CNNsPublication . Perre, Ana Catarina; Alexandre, Luís; Freire, Luís C.In order to improve the performance of Convolutional Neural Networks (CNN) in the classification of mammographic images, many researchers choose to apply a normalization method during the pre-processing stage. In this work, we aimed to assess the impact of 6 different normalization methods in the classification performance of 2 CNNs. We have also explored 5 classifiers, being the first one the CNN itself. The other 4 correspond to Support Vector Machine (SVM), Random Forest (RF), Simple Logistic (SL) and Voted Perceptron (VP) classifiers, all of them fed with features extracted from one of the layers - comprised between the sixteenth and the nineteenth - of the CNN. The last 3 classifiers were tested with different options for data testing presentation, according to theWeka software: Supplied Test Set (STS), 10-fold Cross Validation (10-FCV) and Percentage Split (PS). Results indicate that the effect of image normalization in the performance of the CNNs depends on which network is chosen to make the classification; besides, the normalization method that seems to have the most positive impact is the one that subtracts to each image the corresponding image mean and divide it by the standard deviation (best AUC mean values were 0.786 for CNN-F and 0.790 for Caffe; the best run AUC values were, respectively, 0.793 and 0.791. Layer 1 freezing decreased the running time and did not harm the classification performance. Regarding the different classifiers, CNNs used alone with softmax yielded the best results, with the exception of the RF and SL classifiers, both using the 10-FCV and PS options; however, with these options, we cannot guarantee that the test set images are presented for the first time to the network.
- Image Sentiment Analysis: Experimental Evaluation of Several Deep Learning ArchitecturesPublication . Gaspar, António; Alexandre, LuísImage sentiment analysis is an important topic nowadays. It is possible to use it to classify an image at sentiment level, as negative, neutral or positive. However, to classify an image at this level is a hard challenge because its semantic meaning can represent many scenarios. In this paper, we present an analysis of several image classification methods that we evaluate to improve the state of the art in a large tweet data set.
- Improving Grasping Performance by Segmentation of Large Planar SurfacePublication . Lopes, Vasco; Alexandre, LuísGrasping objects is a task that humans do without major concerns. This results from learning and observing other skilled humans doing such task and with previous information, unconsciously, we know how to pick up different types of objects. However, grasping novel objects in unknown positions for a robot is a complex task which encounters many problems, such as the performance rates that are not perfect and the time consumption. In this paper we present a method that complements the state-ofthe- art grasping by removing the largest planar surface of the image of the world before the grasp detector receives them. The proposed method improves the performance rate and is also capable of reducing the time consumption.
- «
- 1 (current)
- 2
- 3
- »