Related papers: An FPGA-Based On-Device Reinforcement Learning App…
A convenient approach to optimally solving combinatorial optimization tasks is the Branch-and-Bound method. Its branching heuristic can be learned to solve a large set of similar tasks. The promising results here are achieved by the…
Recurrent Neural Networks (RNNs) are powerful models that achieve exceptional performance on several pattern recognition problems. However, the training of RNNs is a computationally difficult task owing to the well-known…
As the backbone technology of machine learning, deep neural networks (DNNs) have have quickly ascended to the spotlight. Running DNNs on resource-constrained mobile devices is, however, by no means trivial, since it incurs high performance…
$Q$-learning is the most fundamental model-free reinforcement learning algorithm. Deployment of $Q$-learning requires approximation of the state-action value function (also known as the $Q$-function). In this work, we provide online random…
With the rapid advance of information technology, network systems have become increasingly complex and hence the underlying system dynamics are often unknown or difficult to characterize. Finding a good network control policy is of…
Despite the great empirical success of deep reinforcement learning, its theoretical foundation is less well understood. In this work, we make the first attempt to theoretically understand the deep Q-network (DQN) algorithm (Mnih et al.,…
Training deep neural networks at the edge on light computational devices, embedded systems and robotic platforms is nowadays very challenging. Continual learning techniques, where complex models are incrementally trained on small batches of…
NDN has gained significant attention due to the appearance of several unforeseen design flaws that became evident with new communication scenarios. Among its many features, the two standard NDN forwarding strategies are not adaptive,…
The increased demand for data privacy and security in machine learning (ML) applications has put impetus on effective edge training on Internet-of-Things (IoT) nodes. Edge training aims to leverage speed, energy efficiency and adaptability…
Deep learning applications have achieved great success in numerous real-world applications. Deep learning models, especially Convolution Neural Networks (CNN) are often prototyped using FPGA because it offers high power efficiency and…
The performance of deep reinforcement learning agents is fundamentally constrained by their neural network architecture, a choice traditionally made through expensive hyperparameter searches and then fixed throughout training. This work…
Almost in every heavily computation-dependent application, from 6G communication systems to autonomous driving platforms, a large portion of computing should be near to the client side. Edge computing (AI at Edge) in mobile devices is one…
This paper studies the joint beamwidth and transmit power optimization problem in millimeter wave communication systems. A deep reinforcement learning based approach is proposed. Specifically, a customized deep Q network is trained offline,…
In this article, we propose a novel algorithm for deep reinforcement learning named Expert Q-learning. Expert Q-learning is inspired by Dueling Q-learning and aims at incorporating semi-supervised learning into reinforcement learning…
Phishing is a cybercrime in which individuals are deceived into revealing personal information, often resulting in financial loss. These attacks commonly occur through fraudulent messages, misleading advertisements, and compromised…
Deep Reinforcement Learning (RL) methods rely on experience replay to approximate the minibatched supervised learning setting; however, unlike supervised learning where access to lots of training data is crucial to generalization,…
Object detection plays a crucial role in smart video analysis, with applications ranging from autonomous driving and security to smart cities. However, achieving real-time object detection on edge devices presents significant challenges due…
FPGAs have been shown to be a promising platform for deploying Quantised Neural Networks (QNNs) with high-speed, low-latency, and energy-efficient inference. However, the complexity of modern deep-learning models limits the performance on…
We consider a distributed system, consisting of a heterogeneous set of devices, ranging from low-end to high-end. These devices have different profiles, e.g., different energy budgets, or different hardware specifications, determining their…
Deep neural network (DNN) based approaches hold significant potential for reinforcement learning (RL) and have already shown remarkable gains over state-of-art methods in a number of applications. The effectiveness of DNN methods can be…