In this paper, we introduce a novel scheme for the separate training of deep learning-based autoencoders used for Channel State Information (CSI) feedback. Our distinct training approach caters to multiple users and b...In this paper, we introduce a novel scheme for the separate training of deep learning-based autoencoders used for Channel State Information (CSI) feedback. Our distinct training approach caters to multiple users and base stations, enabling independent and individualized local training. This ensures the more secure processing of data and algorithms, different from the commonly adopted joint training method. To maintain comparable performance with joint training, we present two distinct training methods: separate training decoder and separate training encoder. It’s noteworthy that conducting separate training for the encoder can pose additional challenges, due to its responsibility in acquiring a compressed representation of underlying data features. This complexity makes accommodating multiple pre-trained decoders for just one encoder a demanding task. To overcome this, we design an adaptation layer architecture that effectively minimizes performance losses. Moreover, the flexible training strategy empowers users and base stations to seamlessly incorporate distinct encoder and decoder structures into the system, significantly amplifying the system’s scalability. .展开更多
In this paper,we experimentally demonstrate ultrafast optical control of slow light in the terahertz(THz) range by combining the electromagnetically induced transparency(EIT) metasurfaces with the cut wire made of P+-...In this paper,we experimentally demonstrate ultrafast optical control of slow light in the terahertz(THz) range by combining the electromagnetically induced transparency(EIT) metasurfaces with the cut wire made of P+-implanted silicon with short carrier lifetime.Employing the optical-pump THz-probe spectroscopy,we observed that the device transited from a state with a slow light effect to a state without a slow light effect in an ultrafast time of 5 ps and recovered within 200 ps.A coupled oscillator model is utilized to explain the origin of controllability.The experimental results agree very well with the simulated and theoretical results.These EIT metasurfaces have the potential to be used as an ultrafast THz optical delay device.展开更多
文摘In this paper, we introduce a novel scheme for the separate training of deep learning-based autoencoders used for Channel State Information (CSI) feedback. Our distinct training approach caters to multiple users and base stations, enabling independent and individualized local training. This ensures the more secure processing of data and algorithms, different from the commonly adopted joint training method. To maintain comparable performance with joint training, we present two distinct training methods: separate training decoder and separate training encoder. It’s noteworthy that conducting separate training for the encoder can pose additional challenges, due to its responsibility in acquiring a compressed representation of underlying data features. This complexity makes accommodating multiple pre-trained decoders for just one encoder a demanding task. To overcome this, we design an adaptation layer architecture that effectively minimizes performance losses. Moreover, the flexible training strategy empowers users and base stations to seamlessly incorporate distinct encoder and decoder structures into the system, significantly amplifying the system’s scalability. .
基金supported by the National Natural Science Foundation of China (Nos.11704373 and 51627901)Fundamental Research Funds for the Central Universities (No.WK2340000071)+1 种基金Open Programs for the Key Science & Technology Infrastructures of Chinese Academy of Sciences (No.CX2310000100)Anhui Initiative in Quantum Information Technologies (No.AHY100000)。
文摘In this paper,we experimentally demonstrate ultrafast optical control of slow light in the terahertz(THz) range by combining the electromagnetically induced transparency(EIT) metasurfaces with the cut wire made of P+-implanted silicon with short carrier lifetime.Employing the optical-pump THz-probe spectroscopy,we observed that the device transited from a state with a slow light effect to a state without a slow light effect in an ultrafast time of 5 ps and recovered within 200 ps.A coupled oscillator model is utilized to explain the origin of controllability.The experimental results agree very well with the simulated and theoretical results.These EIT metasurfaces have the potential to be used as an ultrafast THz optical delay device.
