Towards On-Device Learning and Reconfigurable Hardware Implementation for Encoded Single-Photon Signal Processing

Deep neural networks (DNNs) enhance the accuracy and efficiency of reconstructing key parameters from time-resolved photon arrival signals recorded by single-photon detectors. However, the performance of conventional backpropagation-based DNNs is highly dependent on various parameters of the optical setup and biological samples under examination, necessitating frequent network retraining, either through transfer learning or from scratch. Newly collected data must also be stored and transferred to a high-performance GPU server for retraining, introducing latency and storage overhead. To address these challenges, we propose an online training algorithm based on a One-Sided Jacobi rotation-based Online Sequential Extreme Learning Machine (OSOS-ELM). We fully exploit parallelism in executing OSOS-ELM on a heterogeneous FPGA with integrated ARM cores. Extensive evaluations of OSOS-ELM and OSELM demonstrate that both achieve comparable accuracy across different network dimensions (i.e., input, hidden, and output layers), while OSOS-ELM proves to be more hardware-efficient. By leveraging the parallelism of OSOS-ELM, we implement a holistic computing prototype on a Xilinx ZCU104 FPGA, which integrates a multi-core CPU and programmable logic fabric. We validate our approach through three case studies involving single-photon signal analysis: sensing through fog using commercial single-photon LiDAR, fluorescence lifetime estimation in FLIM, and blood flow index reconstruction in DCS, all utilizing one-dimensional data encoded from photonic signals. From a hardware perspective, we optimize the OSOS-ELM workload by employing multi-tasked processing on ARM CPU cores and pipelined execution on the FPGA's logic fabric. We also implement our OSOS-ELM on the NVIDIA Jetson Xavier NX GPU to comprehensively investigate its computing performance on another type of heterogeneous computing platform.

Analyzable Chain-of-Musical-Thought Prompting for High-Fidelity Music Generation

Autoregressive (AR) models have demonstrated impressive capabilities in generating high-fidelity music. However, the conventional next-token prediction paradigm in AR models does not align with the human creative process in music composition, potentially compromising the musicality of generated samples. To overcome this limitation, we introduce MusiCoT, a novel chain-of-thought (CoT) prompting technique tailored for music generation. MusiCoT empowers the AR model to first outline an overall music structure before generating audio tokens, thereby enhancing the coherence and creativity of the resulting compositions. By leveraging the contrastive language-audio pretraining (CLAP) model, we establish a chain of "musical thoughts", making MusiCoT scalable and independent of human-labeled data, in contrast to conventional CoT methods. Moreover, MusiCoT allows for in-depth analysis of music structure, such as instrumental arrangements, and supports music referencing -- accepting variable-length audio inputs as optional style references. This innovative approach effectively addresses copying issues, positioning MusiCoT as a vital practical method for music prompting. Our experimental results indicate that MusiCoT consistently achieves superior performance across both objective and subjective metrics, producing music quality that rivals state-of-the-art generation models. Our samples are available at https://MusiCoT.github.io/.

Spiking Neural Network Enhanced Hand Gesture Recognition Using Low-Cost Single-photon Avalanche Diode Array

We present a compact spiking convolutional neural network (SCNN) and spiking multilayer perceptron (SMLP) to recognize ten different gestures in dark and bright light environments, using a $9.6 single-photon avalanche diode (SPAD) array. In our hand gesture recognition (HGR) system, photon intensity data was leveraged to train and test the network. A vanilla convolutional neural network (CNN) was also implemented to compare the performance of SCNN with the same network topologies and training strategies. Our SCNN was trained from scratch instead of being converted from the CNN. We tested the three models in dark and ambient light (AL)-corrupted environments. The results indicate that SCNN achieves comparable accuracy (90.8%) to CNN (92.9%) and exhibits lower floating operations with only 8 timesteps. SMLP also presents a trade-off between computational workload and accuracy. The code and collected datasets of this work are available at https://github.com/zzy666666zzy/TinyLiDAR_NET_SNN.

Fast Cerebral Blood Flow Analysis via Extreme Learning Machine

We introduce a rapid and precise analytical approach for analyzing cerebral blood flow (CBF) using Diffuse Correlation Spectroscopy (DCS) with the application of the Extreme Learning Machine (ELM). Our evaluation of ELM and existing algorithms involves a comprehensive set of metrics. We assess these algorithms using synthetic datasets for both semi-infinite and multi-layer models. The results demonstrate that ELM consistently achieves higher fidelity across various noise levels and optical parameters, showcasing robust generalization ability and outperforming iterative fitting algorithms. Through a comparison with a computationally efficient neural network, ELM attains comparable accuracy with reduced training and inference times. Notably, the absence of a back-propagation process in ELM during training results in significantly faster training speeds compared to existing neural network approaches. This proposed strategy holds promise for edge computing applications with online training capabilities.

Enhancing Blood Flow Assessment in Diffuse Correlation Spectroscopy: A Transfer Learning Approach with Noise Robustness Analysis

Diffuse correlation spectroscopy (DCS) is an emerging noninvasive technique that measures the tissue blood flow, by using near-infrared coherent point-source illumination to detect spectral changes. While machine learning has demonstrated significant potential for measuring blood flow index (BFi), an open question concerning the success of this approach pertains to its robustness in scenarios involving deviations between datasets with varying Signal-to-Noise Ratios (SNRs) originating from diverse clinical applications and various setups. This study proposes a transfer learning approach, aims to assess the influence of SNRs on the generalization ability of learned features, and demonstrate the robustness for transfer learning. A synthetic dataset with varying levels of added noise is utilized to simulate different SNRs. The proposed network takes a 1x64 autocorrelation curve as input and generates BFi and the correlation parameter beta. The proposed model demonstrates excellent performance across different SNRs, exhibiting enhanced fitting accuracy, particularly for low SNR datasets when compared with other fitting methods. This highlights its potential for clinical diagnosis and treatment across various scenarios under different clinical setups.