Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userCompatible Learning for Deep Photonic Neural Network
170
0
0.0
(
0
)
Ask ChatGPT about the research
No Arabic abstract
Realization of deep learning with coherent optical field has attracted remarkably attentions presently, which benefits on the fact that optical matrix manipulation can be executed at speed of light with inherent parallel computation as well as low latency. Photonic neural network has a significant potential for prediction-oriented tasks. Yet, real-value Backpropagation behaves somewhat intractably for coherent photonic intelligent training. We develop a compatible learning protocol in complex space, of which nonlinear activation could be selected efficiently depending on the unveiled compatible condition. Compatibility indicates that matrix representation in complex space covers its real counterpart, which could enable a single channel mingled training in real and complex space as a unified model. The phase logical XOR gate with Mach-Zehnder interferometers and diffractive neural network with optical modulation mechanism, implementing intelligent weight learned from compatible learning, are presented to prove the availability. Compatible learning opens an envisaged window for deep photonic neural network.
rate research
Read More
Owing to the complicated characteristics of 5G communication system, designing RF components through mathematical modeling becomes a challenging obstacle. Moreover, such mathematical models need numerous manual adjustments for various specification requirements. In this paper, we present a learning-based framework to model and compensate Power Amplifiers (PAs) in 5G communication. In the proposed framework, Deep Neural Networks (DNNs) are used to learn the characteristics of the PAs, while, correspondent Digital Pre-Distortions (DPDs) are also learned to compensate for the nonlinear and memory effects of PAs. On top of the framework, we further propose two frequency domain losses to guide the learning process to better optimize the target, compared to naive time domain Mean Square Error (MSE). The proposed framework serves as a drop-in replacement for the conventional approach. The proposed approach achieves an average of 56.7% reduction of nonlinear and memory effects, which converts to an average of 16.3% improvement over a carefully-designed mathematical model, and even reaches 34% enhancement in severe distortion scenarios.
In this paper, we are interested in building a domain knowledge based deep learning framework to solve the chiller plants energy optimization problems. Compared to the hotspot applications of deep learning (e.g. image classification and NLP), it is difficult to collect enormous data for deep network training in real-world physical systems. Most existing methods reduce the complex systems into linear model to facilitate the training on small samples. To tackle the small sample size problem, this paper considers domain knowledge in the structure and loss design of deep network to build a nonlinear model with lower redundancy function space. Specifically, the energy consumption estimation of most chillers can be physically viewed as an input-output monotonic problem. Thus, we can design a Neural Network with monotonic constraints to mimic the physical behavior of the system. We verify the proposed method in a cooling system of a data center, experimental results show the superiority of our framework in energy optimization compared to the existing ones.
Photonic signal processing is essential in the optical communication and optical computing. Numerous photonic signal processors have been proposed, but most of them exhibit limited reconfigurability and automaticity. A feature of fully automatic implementation and intelligent response is highly desirable for the multipurpose photonic signal processors. Here, we report and experimentally demonstrate a fully self-learning and reconfigurable photonic signal processor based on an optical neural network chip. The proposed photonic signal processor is capable of performing various functions including multichannel optical switching, optical multiple-input-multiple-output descrambler and tunable optical filter. All the functions are achieved by complete self-learning. Our demonstration suggests great potential for chip-scale fully programmable optical signal processing with artificial intelligence.
A neural network is essentially a high-dimensional complex mapping model by adjusting network weights for feature fitting. However, the spectral bias in network training leads to unbearable training epochs for fitting the high-frequency components in broadband signals. To improve the fitting efficiency of high-frequency components, the PhaseDNN was proposed recently by combining complex frequency band extraction and frequency shift techniques [Cai et al. SIAM J. SCI. COMPUT. 42, A3285 (2020)]. Our paper is devoted to an alternative candidate for fitting complex signals with high-frequency components. Here, a parallel frequency function-deep neural network (PFF-DNN) is proposed to suppress computational overhead while ensuring fitting accuracy by utilizing fast Fourier analysis of broadband signals and the spectral bias nature of neural networks. The effectiveness and efficiency of the proposed PFF-DNN method are verified based on detailed numerical experiments for six typical broadband signals.
Implanted devices providing real-time neural activity classification and control are increasingly used to treat neurological disorders, such as epilepsy and Parkinsons disease. Classification performance is critical to identifying brain states appropriate for the therapeutic action. However, advanced algorithms that have shown promise in offline studies, in particular deep learning (DL) methods, have not been deployed on resource-restrained neural implants. Here, we designed and optimized three embedded DL models of commonly adopted architectures and evaluated their inference performance in a case study of seizure detection. A deep neural network (DNN), a convolutional neural network (CNN), and a long short-term memory (LSTM) network were designed to classify ictal, preictal, and interictal phases from the CHB-MIT scalp EEG database. After iterative model compression and quantization, the algorithms were deployed on a general-purpose, off-the-shelf microcontroller. Inference sensitivity, false positive rate, execution time, memory size, and power consumption were quantified. For seizure event detection, the sensitivity and FPR (h-1) for the DNN, CNN, and LSTM models were 87.36%/0.169, 96.70%/0.102, and 97.61%/0.071, respectively. Predicting seizures for early warnings was also feasible. The implemented compression and quantization achieved a significant saving of power and memory with an accuracy degradation of less than 0.5%. Edge DL models achieved performance comparable to many prior implementations that had no time or computational resource limitations. Generic microcontrollers can provide the required memory and computational resources, while model designs can be migrated to ASICs for further optimization. The results suggest that edge DL inference is a feasible option for future neural implants to improve classification performance and therapeutic outcomes.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
