This paper presents a hardware accelerated implementation of a complete Versatile Video Coding (VVC) video decoder on an Arty Z7-20 FPGA board. In this work, we have ported the original C++ source code, released as op...
详细信息
My research explores integrating deep learning and logic programming to set the basis for a new generation of AI systems. By combining neural networks with Inductive logic Programming (ILP), the goal is to construct s...
详细信息
My research explores integrating deep learning and logic programming to set the basis for a new generation of AI systems. By combining neural networks with Inductive logic Programming (ILP), the goal is to construct systems that make accurate predictions and generate comprehensible rules to validate these predictions. Deep learning models process and analyze complex data, while ILP techniques derive logical rules to prove the network's conclusions. Explainable AI methods, like eXplainable Answer Set Programming (XASP), elucidate the reasoning behind these rules and decisions. The focus is on applying ILP frameworks, specifically ILASP and FastLAS, to enhance explainability in various domains. My test cases span weather prediction, the legal field, and image recognition. In weather forecasting, the system will predict events and provides explanations using FastLAS, with plans to integrate recurrent neural networks in the future. In the legal domain, the research focuses on interpreting vague decisions and assisting legal professionals by encoding Italian legal articles and learning reasoning patterns from Court of Cassation decisions using ILASP. For biological laboratories, we will collaborate with a research group to automate spermatozoa morphology classification for Bull Breeding Soundness Evaluation using YOLO networks and ILP to explain classification outcomes. This hybrid approach aims to bridge the gap between the high performance of deep learning models and the transparency of symbolic reasoning, advancing AI by providing interpretable and trustworthy applications.
This paper designed and developed a mobile intelligent diagnosis system for gallstone disease based on deep learning. It can be used offline on Android phones to realize automatic recognition of medical images of gall...
详细信息
ISBN:
(数字)9798350360240
ISBN:
(纸本)9798350384161
This paper designed and developed a mobile intelligent diagnosis system for gallstone disease based on deep learning. It can be used offline on Android phones to realize automatic recognition of medical images of gallstone disease. This project intends to take Xilinx company's newly released ZYNQ Super Scale+ MPSoC as the research object, and innovatively introduce it to the hardware and software platform. ARM and FPGA (fieldprogrammablelogic Gate Array) work together to achieve high-performance computing capabilities that Gpus common to machine learning cannot match. Experiments have proved that the Google network trained by transplantation can classify gallstones with an accuracy of more than 98%, which is comparable to experienced doctors. It can realize a full identification of gallstone disease and can be completed in 2 seconds. Compared with GPU, this algorithm has the advantages of fast processing speed, low power consumption, and good user experience. It is easy to carry and has a wide range of applications.
An emerging trend in power electronics control is the use of controllers based on a system-on-a-chip (SoC). SoCs provide a high-performance computing platform by embedding one or multiple processors and a field-progra...
详细信息
ISBN:
(数字)9781665496810
ISBN:
(纸本)9781665496810
An emerging trend in power electronics control is the use of controllers based on a system-on-a-chip (SoC). SoCs provide a high-performance computing platform by embedding one or multiple processors and a field-programmable gate array (FPGA) on the same chip. This paper reviews SoCs for power electronics control applications, discussing aspects such as task allocations and available hardware and software tools. A design and experimental results of an SoC-based controller are discussed, and some of the SoC-based platforms built by researchers in power electronics control are reviewed.
Hummingbird E203, as a commonly used processor based on the RISC-V architecture, possesses excellent performance and extensive applications. Addressing the scarcity of applications in developing game for the Hummingbi...
详细信息
Simulated Annealing (SA) has been used successfully with a broad spectrum of optimization problems, including the optimization of Fuzzy logic Systems (FLS). A suitable formation of SA, however, is dependent on the sel...
详细信息
Approximate computing has become a viable method for achieving major power and energy savings in computer systems in recent years. It is frequently used in computationally demanding, fault-tolerant systems that requir...
详细信息
The main objective of Input/Output (IO) standard is to match the impedance of input and output port along with FPGA device. During our research, we observe that different IO standards is taking different power but fun...
详细信息
Convolutional neural networks (CNNs) have been widely recognized and applied in the field of robotics. However, the huge amount of computation and parameters of CNN bring great challenges to its deployment on mobile t...
详细信息
Quasi delay insensitive (QDI) circuits, as a type of asynchronous circuits, have unique advantages such as high robustness, low power consumption, and event driven, so they have the potential to be applied in fields s...
详细信息
暂无评论