Search

Wireless implantable devices are widely used in medical treatment, which should meet clinical constraints such as longevity, miniaturization, and reliable communication. Wireless power transfer (WPT) can eliminate the battery to reduce system size and prolong device life, while it's challenging to generate a reliable clock without a crystal. In this work, we propose a self-adaptive dual-injection-locked-ring-oscillator (dual-ILRO) clock-recovery technique based on two-tone WPT and integrate it into a battery-free neural-recording SoC. The 2$\text{nd}$-order inter-modulation (IM2) component of the two WPT tones is extracted as a low-frequency reference for battery-free SoC, and the proposed self-adaptive dual-ILRO technique extends the lock range to ensure an anti-interference PVT-robust clock generation. The neural-recording SoC includes a low-noise signal acquisition unit, a power management unit, and a backscatter circuit to perform neural signal recording, wireless power harvesting, and neural data transmission. Benefiting from the 6.4 $\mu$W low power of the clock recovery circuit, the overall SoC power is cut down to 49.8 $\mu$W. In addition, the proposed clock-recovery technique enables both signal acquisition and uplink communication to perform as well as that synchronized by an ideal clock, i.e., an effective number of 9.6 bits and a bit error rate (BER) less than 4.8 $\times\, 10^{-7}$ in chip measurement. The SoC takes a die area of 2.05 mm$^{2}$, and an animal test is conducted in a Sprague-Dawley rat to validate the wireless neural-recording performance, compared to a crystal-synchronized commercial chip.

This paper proposes a novel pipeline to estimate a non-parametric environment map with high dynamic range from a single human face image. Lighting-independent and -dependent intrinsic images of the face are first estimated separately in a cascaded network. The influence of face geometry on the two lighting-dependent intrinsics, diffuse shading and specular reflection, are further eliminated by distributing the intrinsics pixel-wise onto spherical representations using the surface normal as indices. This results in two representations simulating images of a diffuse sphere and a glossy sphere under the input scene lighting. Taking into account the distinctive nature of light sources and ambient terms, we further introduce a two-stage lighting estimator to predict both accurate and realistic lighting from these two representations. Our model is trained supervisedly on a large-scale and high-quality synthetic face image dataset. We demonstrate that our method allows accurate and detailed lighting estimation and intrinsic decomposition, outperforming state-of-the-art methods both qualitatively and quantitatively on real face images.

Thanks to their event-driven nature, spiking neural networks (SNNs) enjoy great energy efficiency and are believed to be a viable solution to the power wall problem. Due to difficulty in direct training, researchers have proposed indirect conversion-based methods, which allow SNNs to achieve comparable accuracy to their original nonspiking counterparts. However, most of these methods focus on classification problems; object detection with SNN, which involves a more challenging regression problem, remains an open research problem. The only existing SNN-based object detection method Spiking YOLO relied on a modified integrate-and-fire (IF) neuron model with two firing thresholds, which is not supported by most neuromorphic hardware. In order to run object detection on neuromorphic hardware, we propose a region-based SNN (R-SNN) with widely adopted IF neurons. The bounding box regressor uses mirror output neurons along with the original output neurons to represent both positive and negative bounding box offsets, and decodes the output spike trains with a simple bounding box recovery algorithm to recover real-valued bounding box offsets. Moreover, we deploy our R-SNN on our neuromorphic computing system “Darwin Mouse” to develop a low-power object detection application, demonstrating the feasibility of applying our method to real-world neuromorphic hardware with limited arithmetic precision. Experiments show that our R-SNN achieves a mean average precision (mAP) of 63.1% on VOC 2007, improving the state of the art (achieved by Spiking YOLO) by more than 11%.

Thanks to their event-driven nature, spiking neural networks (SNNs) are surmised to be great computation-efficient models. The spiking neurons encode beneficial temporal facts and possess excessive anti-noise properties. However, the high-quality encoding of spatio-temporal complexity and also its training optimization of SNNs are restricted by means of the contemporary problem, this article proposes a novel hierarchical event-driven visual device to explore how information transmits and signifies in the retina the usage of biologically manageable mechanisms. This cognitive model is an augmented spiking-based framework consisting of the function learning capacity of convolutional neural networks (CNNs) with the cognition capability of SNNs. Furthermore, this visual device is modeled in a biological realism way with unsupervised learning rules and advanced spike firing rate encoding methods. We train and test them on some image datasets (Modified National Institute of Standards and Technology (MNIST), Canadian Institute for Advanced Research (CIFAR)10, and its noisy versions) to show that our mannequin can process greater vital data than present cognitive models. This article also proposes a novel quantization approach to make the proposed spiking-based model more efficient for neuromorphic hardware implementation. The outcomes show this joint CNN-SNN model can reap excessive focus accuracy and get more effective generalization ability.