An Interpretable and Accurate Deep-Learning

 The deployment of automated deep-learning classifiers in clinical practice has the potential to streamline the diagnosis process and improve the diagnosis accuracy, but the acceptance of those classifiers relies on both their accuracy and interpretability. In general, accurate deep-learning classifiers provide little model interpretability, whi...

DNNs CNN DP Machine Learning

META-TRANSFER LEARNING THROUGH HARD TASKS

 Meta-learning has been proposed as a framework to address the challenging few-shot learning setting. The key idea is to leverage a large number of similar few-shot tasks in order to learn how to adapt a base-learner to a new task for which only a few labeled samples are available. As deep neural networks (DNNs) tend to overfit using a few samples o...

MACHINE LEARNING META-TRANSFER

Development of the Mobile Robot with a Robot Arm

 The purpose of this study is to design a prototype of a mobile robot equipped with a robotic arm which can be controlled by wireless technology. In this scheme, the mobile robot in the form of 6 Wheel Drive Robot equipped with robotic arm 6 Degree of Freedom and is controlled wirelessly through remote control based on XBee Pro Series 1. Data on the...

DNNOff Offloading DNN-based Intelligent IoT Applications in Mobile Edge Computing

 Deep neural network (DNN) has become increasingly popular in industrial IoT scenarios. Due to high demands on computational capability, it is hard for DNN-based applications to directly run on intelligent end devices with limited resources. Computation offloading technology offers a feasible solution by offloading some computation-intensive tasks t...

Emotional Semantics-Preserved and Feature-Aligned Cycle GAN for Visual Emotion Adaptation

 Thanks to large-scale labeled training data, deep neural networks (DNNs) have obtained remarkable success in many vision and multimedia tasks. However, because of the presence of domain shift, the learned knowledge of the well-trained DNNs cannot be well generalized to new domains or datasets that have few labels. Unsupervised domain adaptation (UD...

Federated Tensor Decomposition-Based Feature Extraction Approach for Industrial IoT

 Data in modern industrial applications and data science presents multidimensional progressively, the dimension and the structural complexity of these data are becoming extremely high, which renders existing data analysis methods and machine learning algorithms inadequate to the extent. In addition, high-dimensional data in actual scenarios often sh...

XpulpNN Enabling Energy Efficient and Flexible Inference of Quantized Neural Networks on RISC-V based IoT End Nodes

 Strongly quantized fixed-point arithmetic is now considered a well-established solution to deploy Convolutional Neural Networks (CNNs) on limited-memory low-power IoT endnodes. Such a trend is challenging due to the lack of support for low bitwidth fixed-point instructions in the Instruction Set Architecture (ISA) of state-of-the-art embedded Micro...

DORY Automatic End-to-End Deployment of Real-World DNNs on Low-Cost IoT MCUs

 The deployment of Deep Neural Networks (DNNs) on end-nodes at the extreme edge of the Internet-of-Things is a critical enabler to support pervasive Deep Learning-enhanced applications. Low-Cost MCU-based end-nodes have limited on-chip memory and often replace caches with scratchpads, to reduce area overheads and increase energy efficiency – requiri...