Changes in Receptive Field Size in Syngap1 +/- Mouse Model of Autism Spectrum Disorder

Background and Hypothesis: Autism spectrum disorder (ASD) is a form of intellectual disability with impairments in social functioning and cognition. Mutations within the SynGAP1 gene are associated with ASD due to over activation of RAS-GTP causing insertion of AMPA receptors onto the post synaptic membrane, and thus early maturation of dendrites. These mutations lead to an excitatory/inhibitory imbalance within the brain, and patients often present with intellectual disability, seizures, and issues of cognition. Research has shown that Syngap1 +/- mice have decreased cortical gray matter brain volume throughout areas involved in the visual system pathway. However, hierarchal visual processing has not been well characterized in a Syngap1 +/- mouse model of autism. Project Methods: Using 64 and 128 channel microelectrodes, we recorded the neural activity within V1 of four mice. Neural activity was recorded in response to visual stimuli - testing receptive field size between two wild-type and two Syngap1 +/- mice. Data was run through spike sorting algorithms to identify neurons. Receptive field area for each neuron was then calculated and compared between the two genotypes. Results: The receptive field areas of Syngap1 +/- mice were statistically larger (p < 0.01) compared to wild type mice. Syngap1 +/- mice had a mean receptive field area of 450.5 visual degrees (±443.7) and WT mice had a mean receptive field area of 261.1 visual degrees (±187.21). Most of the neurons within Syngap +/- had no distinct receptive field, 67.9%, while only 25.7% of wild type neurons lacked a distinct receptive field. Conclusion and Potential Impact: Overall, Syngap1 +/- mice had larger, and less distinct receptive fields compared to wild type mice. Deficiencies in the Syngap1 protein may impair refinement of visual stimuli. Understanding the mechanism of response of missing SynGAP1 can inform directed therapies and interventions to treat patients with the missing gene and manage their intellectual disability.

A PCB Electronic Components Detection Network Design Based on Effective Receptive Field Size and Anchor Size Matching

Vision-based recognizing and positioning of electronic components on the PCB (printed circuit board) can improve the quality inspection efficiency of electronic products in the manufacturing process. With the improvement of the design and the production process, the electronic components on the PCB show the characteristics of small sizes and similar appearances, which brings challenges to visual object detection. This paper designs a real-time electronic component detection network through effective receptive field size and anchor size matching in YOLOv3. We make contributions in the following three aspects: (1) realizing the calculation and visualization of the effective receptive field size of the different depth layers of the CNN (convolutional neural network) based on gradient backpropagation; (2) proposing a modular YOLOv3 composition strategy that can be added and removed; and (3) designing a lightweight and efficient detection network by effective receptive field size and anchor size matching algorithm. Compared with the Faster-RCNN (regions with convolutional neural network) features, SSD (single-shot multibox detectors), and original YOLOv3, our method not only has the highest detection mAP (mean average precision) on the PCB electronic component dataset, which is 95.03%, the smallest parameter size of the memory, about 1/3 of the original YOLOv3 parameter amount, but also the second-best performance on FLOPs (floating point operations).

Text Detection Using Multi-Stage Region Proposal Network Sensitive to Text Scale

Recently, attention has surged concerning intelligent sensors using text detection. However, there are challenges in detecting small texts. To solve this problem, we propose a novel text detection CNN (convolutional neural network) architecture sensitive to text scale. We extract multi-resolution feature maps in multi-stage convolution layers that have been employed to prevent losing information and maintain the feature size. In addition, we developed the CNN considering the receptive field size to generate proposal stages. The experimental results show the importance of the receptive field size.

Pixel-Aware Deep Function-Mixture Network for Spectral Super-Resolution

Spectral super-resolution (SSR) aims at generating a hyperspectral image (HSI) from a given RGB image. Recently, a promising direction is to learn a complicated mapping function from the RGB image to the HSI counterpart using a deep convolutional neural network. This essentially involves mapping the RGB context within a size-specific receptive field centered at each pixel to its spectrum in the HSI. The focus thereon is to appropriately determine the receptive field size and establish the mapping function from RGB context to the corresponding spectrum. Due to their differences in category or spatial position, pixels in HSIs often require different-sized receptive fields and distinct mapping functions. However, few efforts have been invested to explicitly exploit this prior.To address this problem, we propose a pixel-aware deep function-mixture network for SSR, which is composed of a new class of modules, termed function-mixture (FM) blocks. Each FM block is equipped with some basis functions, i.e., parallel subnets of different-sized receptive fields. Besides, it incorporates an extra subnet as a mixing function to generate pixel-wise weights, and then linearly mixes the outputs of all basis functions with those generated weights. This enables us to pixel-wisely determine the receptive field size and the mapping function. Moreover, we stack several such FM blocks to further increase the flexibility of the network in learning the pixel-wise mapping. To encourage feature reuse, intermediate features generated by the FM blocks are fused in late stage, which proves to be effective for boosting the SSR performance. Experimental results on three benchmark HSI datasets demonstrate the superiority of the proposed method.