Structured connectivity in the cerebellum enables noise-resilient pattern separation

The cerebellum is thought to detect and correct errors between intended and executed commands1-3 and is critical for social behaviors, cognition and emotion4-6. Computations for motor control must be performed quickly to correct errors in real time and should be sensitive to small differences between patterns for fine error correction while being resilient to noise7. Influential theories of cerebellar information processing have largely assumed random network connectivity, which increases the encoding capacity of the network's first layer8-13. However, maximizing encoding capacity reduces resiliency to noise7. To understand how neuronal circuits address this fundamental tradeoff, we mapped the feedforward connectivity in the mouse cerebellar cortex using automated large-scale transmission electron microscopy (EM) and convolutional neural network-based image segmentation. We found that both the input and output layers of the circuit exhibit redundant and selective connectivity motifs, which contrast with prevailing models. Numerical simulations suggest these redundant, non-random connectivity motifs increase discriminability of similar input patterns at a minimal cost to the network's overall encoding capacity. This work reveals how neuronal network structure can balance encoding capacity and redundancy, unveiling principles of biological network architecture with implications for artificial neural network design.

Download Full-text

Non-Blind Image Deconvolution Based on “Ringing” Removal Using Convolutional Neural Network

Electronic Imaging ◽

10.2352/issn.2470-1173.2020.10.ipas-180 ◽

2020 ◽

Vol 2020 (10) ◽

pp. 181-1-181-7

Author(s):

Takahiro Kudo ◽

Takanori Fujisawa ◽

Takuro Yamaguchi ◽

Masaaki Ikehara

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Network Architecture ◽

Large Scale ◽

Blind Deconvolution ◽

Training Dataset ◽

Image Deconvolution ◽

Classic Problem ◽

Key Points ◽

Blind Image

Image deconvolution has been an important issue recently. It has two kinds of approaches: non-blind and blind. Non-blind deconvolution is a classic problem of image deblurring, which assumes that the PSF is known and does not change universally in space. Recently, Convolutional Neural Network (CNN) has been used for non-blind deconvolution. Though CNNs can deal with complex changes for unknown images, some CNN-based conventional methods can only handle small PSFs and does not consider the use of large PSFs in the real world. In this paper we propose a non-blind deconvolution framework based on a CNN that can remove large scale ringing in a deblurred image. Our method has three key points. The first is that our network architecture is able to preserve both large and small features in the image. The second is that the training dataset is created to preserve the details. The third is that we extend the images to minimize the effects of large ringing on the image borders. In our experiments, we used three kinds of large PSFs and were able to observe high-precision results from our method both quantitatively and qualitatively.

Download Full-text

SketchGNN: Semantic Sketch Segmentation with Graph Neural Networks

ACM Transactions on Graphics ◽

10.1145/3450284 ◽

2021 ◽

Vol 40 (3) ◽

pp. 1-13

Author(s):

Lumin Yang ◽

Jiajie Zhuang ◽

Hongbo Fu ◽

Xiangzhi Wei ◽

Kun Zhou ◽

...

Keyword(s):

Neural Network ◽

Neural Networks ◽

Network Architecture ◽

Large Scale ◽

State Of The Art ◽

Semantic Segmentation ◽

Structure Information ◽

Graph Neural Networks ◽

Node Labels ◽

Point Level

We introduce SketchGNN , a convolutional graph neural network for semantic segmentation and labeling of freehand vector sketches. We treat an input stroke-based sketch as a graph with nodes representing the sampled points along input strokes and edges encoding the stroke structure information. To predict the per-node labels, our SketchGNN uses graph convolution and a static-dynamic branching network architecture to extract the features at three levels, i.e., point-level, stroke-level, and sketch-level. SketchGNN significantly improves the accuracy of the state-of-the-art methods for semantic sketch segmentation (by 11.2% in the pixel-based metric and 18.2% in the component-based metric over a large-scale challenging SPG dataset) and has magnitudes fewer parameters than both image-based and sequence-based methods.

Download Full-text

Classification of Skin Disease Using Deep Learning Neural Networks with MobileNet V2 and LSTM

Sensors ◽

10.3390/s21082852 ◽

2021 ◽

Vol 21 (8) ◽

pp. 2852

Author(s):

Parvathaneni Naga Srinivasu ◽

Jalluri Gnana SivaSai ◽

Muhammad Fazal Ijaz ◽

Akash Kumar Bhoi ◽

Wonjoon Kim ◽

...

Keyword(s):

Neural Network ◽

Neural Networks ◽

Deep Learning ◽

Convolutional Neural Network ◽

Skin Disease ◽

Network Architecture ◽

Large Scale ◽

Short Term Memory ◽

Convolutional Networks ◽

Occurrence Matrix

Deep learning models are efficient in learning the features that assist in understanding complex patterns precisely. This study proposed a computerized process of classifying skin disease through deep learning based MobileNet V2 and Long Short Term Memory (LSTM). The MobileNet V2 model proved to be efficient with a better accuracy that can work on lightweight computational devices. The proposed model is efficient in maintaining stateful information for precise predictions. A grey-level co-occurrence matrix is used for assessing the progress of diseased growth. The performance has been compared against other state-of-the-art models such as Fine-Tuned Neural Networks (FTNN), Convolutional Neural Network (CNN), Very Deep Convolutional Networks for Large-Scale Image Recognition developed by Visual Geometry Group (VGG), and convolutional neural network architecture that expanded with few changes. The HAM10000 dataset is used and the proposed method has outperformed other methods with more than 85% accuracy. Its robustness in recognizing the affected region much faster with almost 2× lesser computations than the conventional MobileNet model results in minimal computational efforts. Furthermore, a mobile application is designed for instant and proper action. It helps the patient and dermatologists identify the type of disease from the affected region’s image at the initial stage of the skin disease. These findings suggest that the proposed system can help general practitioners efficiently and effectively diagnose skin conditions, thereby reducing further complications and morbidity.

Download Full-text

Data-to-Text Generation with Content Selection and Planning

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v33i01.33016908 ◽

2019 ◽

Vol 33 ◽

pp. 6908-6915 ◽

Cited By ~ 5

Author(s):

Ratish Puduppully ◽

Li Dong ◽

Mirella Lapata

Keyword(s):

Neural Network ◽

Network Architecture ◽

Large Scale ◽

Network Models ◽

Text Generation ◽

Neural Network Models ◽

Generation Task ◽

Content Selection ◽

End To End ◽

Two Stages

Recent advances in data-to-text generation have led to the use of large-scale datasets and neural network models which are trained end-to-end, without explicitly modeling what to say and in what order. In this work, we present a neural network architecture which incorporates content selection and planning without sacrificing end-to-end training. We decompose the generation task into two stages. Given a corpus of data records (paired with descriptive documents), we first generate a content plan highlighting which information should be mentioned and in which order and then generate the document while taking the content plan into account. Automatic and human-based evaluation experiments show that our model1 outperforms strong baselines improving the state-of-the-art on the recently released RotoWIRE dataset.

Download Full-text

An Event-Based Neural Network Architecture with Content Addressable Memory

International Journal of Embedded and Real-Time Communication Systems ◽

10.4018/ijertcs.2020010102 ◽

2020 ◽

Vol 11 (1) ◽

pp. 23-40 ◽

Cited By ~ 3

Author(s):

Sivaganesan S ◽

Maria Antony S ◽

Udayakumar E

Keyword(s):

Neural Network ◽

Network Architecture ◽

Large Scale ◽

Synaptic Weight ◽

Current Mode ◽

Spike Timing ◽

Event Representation ◽

Content Addressable Memory ◽

Neural Computations ◽

Scale Integration

A hybrid analog/digital very large-scale integration (VLSI) implementation of a spiking neural network with programmable synaptic weights was designed. The synaptic weight values are stored in an asynchronous module, which is interfaced to a fast current-mode event-driven DAC for producing synaptic currents with the appropriate amplitude values. It acts as a transceiver, receiving asynchronous events for input, performing neural computations with hybrid analog/digital circuits on the input spikes, and eventually producing digital asynchronous events in output. Input, output, and synaptic weight values are transmitted to/from the chip using a common communication protocol based on the address event representation (AER). Using this representation, it is possible to interface the device to a workstation or a microcontroller and explore the effect of different types of spike-timing dependent plasticity (STDP) learning algorithms for updating the synaptic weights values in the CAM module.

Download Full-text

Memristor Based Binary Convolutional Neural Network Architecture With Configurable Neurons

Frontiers in Neuroscience ◽

10.3389/fnins.2021.639526 ◽

2021 ◽

Vol 15 ◽

Author(s):

Lixing Huang ◽

Jietao Diao ◽

Hongshan Nie ◽

Wei Wang ◽

Zhiwei Li ◽

...

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

High Precision ◽

Network Architecture ◽

Large Scale ◽

Network Performance ◽

Recognition Accuracy ◽

Activation Function ◽

Data Set ◽

Neuron Activation

The memristor-based convolutional neural network (CNN) gives full play to the advantages of memristive devices, such as low power consumption, high integration density, and strong network recognition capability. Consequently, it is very suitable for building a wearable embedded application system and has broad application prospects in image classification, speech recognition, and other fields. However, limited by the manufacturing process of memristive devices, high-precision weight devices are currently difficult to be applied in large-scale. In the same time, high-precision neuron activation function also further increases the complexity of network hardware implementation. In response to this, this paper proposes a configurable full-binary convolutional neural network (CFB-CNN) architecture, whose inputs, weights, and neurons are all binary values. The neurons are proportionally configured to two modes for different non-ideal situations. The architecture performance is verified based on the MNIST data set, and the influence of device yield and resistance fluctuations under different neuron configurations on network performance is also analyzed. The results show that the recognition accuracy of the 2-layer network is about 98.2%. When the yield rate is about 64% and the hidden neuron mode is configured as −1 and +1, namely ±1 MD, the CFB-CNN architecture achieves about 91.28% recognition accuracy. Whereas the resistance variation is about 26% and the hidden neuron mode configuration is 0 and 1, namely 01 MD, the CFB-CNN architecture gains about 93.43% recognition accuracy. Furthermore, memristors have been demonstrated as one of the most promising devices in neuromorphic computing for its synaptic plasticity. Therefore, the CFB-CNN architecture based on memristor is SNN-compatible, which is verified using the number of pulses to encode pixel values in this paper.

Download Full-text

Understanding the Impact of Neural Variations and Random Connections on Inference

Frontiers in Computational Neuroscience ◽

10.3389/fncom.2021.612937 ◽

2021 ◽

Vol 15 ◽

Author(s):

Yuan Zeng ◽

Zubayer Ibne Ferdous ◽

Weixiang Zhang ◽

Mufan Xu ◽

Anlan Yu ◽

...

Keyword(s):

Neural Network ◽

Intelligent System ◽

Design Method ◽

Random Network ◽

Network Connectivity ◽

Processing Technique ◽

Model Parameters ◽

Perceptron Algorithm ◽

The Impact

Recent research suggests that in vitro neural networks created from dissociated neurons may be used for computing and performing machine learning tasks. To develop a better artificial intelligent system, a hybrid bio-silicon computer is worth exploring, but its performance is still inferior to that of a silicon-based computer. One reason may be that a living neural network has many intrinsic properties, such as random network connectivity, high network sparsity, and large neural and synaptic variability. These properties may lead to new design considerations, and existing algorithms need to be adjusted for living neural network implementation. This work investigates the impact of neural variations and random connections on inference with learning algorithms. A two-layer hybrid bio-silicon platform is constructed and a five-step design method is proposed for the fast development of living neural network algorithms. Neural variations and dynamics are verified by fitting model parameters with biological experimental results. Random connections are generated under different connection probabilities to vary network sparsity. A multi-layer perceptron algorithm is tested with biological constraints on the MNIST dataset. The results show that a reasonable inference accuracy can be achieved despite the presence of neural variations and random network connections. A new adaptive pre-processing technique is proposed to ensure good learning accuracy with different living neural network sparsity.

Download Full-text

Robust Negative Sampling for Network Embedding

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v33i01.33013191 ◽

2019 ◽

Vol 33 ◽

pp. 3191-3198 ◽

Cited By ~ 3

Author(s):

Mohammadreza Armandpour ◽

Patrick Ding ◽

Jianhua Huang ◽

Xia Hu

Keyword(s):

Neural Network ◽

Network Architecture ◽

Large Scale ◽

Embedding Problem ◽

Network Embedding ◽

Neural Network Architecture ◽

Suitable Candidate ◽

Computationally Expensive ◽

Large Scale Networks ◽

Method R

Many recent network embedding algorithms use negative sampling (NS) to approximate a variant of the computationally expensive Skip-Gram neural network architecture (SGA) objective. In this paper, we provide theoretical arguments that reveal how NS can fail to properly estimate the SGA objective, and why it is not a suitable candidate for the network embedding problem as a distinct objective. We show NS can learn undesirable embeddings, as the result of the “Popular Neighbor Problem.” We use the theory to develop a new method “R-NS” that alleviates the problems of NS by using a more intelligent negative sampling scheme and careful penalization of the embeddings. R-NS is scalable to large-scale networks, and we empirically demonstrate the superiority of R-NS over NS for multi-label classification on a variety of real-world networks including social networks and language networks.

Download Full-text

Ship Identification and Characterization in Sentinel-1 SAR Images with Multi-Task Deep Learning

Remote Sensing ◽

10.3390/rs11242997 ◽

2019 ◽

Vol 11 (24) ◽

pp. 2997 ◽

Cited By ~ 7

Author(s):

Clément Dechesne ◽

Sébastien Lefèvre ◽

Rodolphe Vadaine ◽

Guillaume Hajduch ◽

Ronan Fablet

Keyword(s):

Neural Network ◽

Deep Learning ◽

Network Architecture ◽

Large Scale ◽

Visual Analysis ◽

Automatic Identification ◽

Identification System ◽

Human Observer ◽

Convolutional Network ◽

Ship Detection

The monitoring and surveillance of maritime activities are critical issues in both military and civilian fields, including among others fisheries’ monitoring, maritime traffic surveillance, coastal and at-sea safety operations, and tactical situations. In operational contexts, ship detection and identification is traditionally performed by a human observer who identifies all kinds of ships from a visual analysis of remotely sensed images. Such a task is very time consuming and cannot be conducted at a very large scale, while Sentinel-1 SAR data now provide a regular and worldwide coverage. Meanwhile, with the emergence of GPUs, deep learning methods are now established as state-of-the-art solutions for computer vision, replacing human intervention in many contexts. They have been shown to be adapted for ship detection, most often with very high resolution SAR or optical imagery. In this paper, we go one step further and investigate a deep neural network for the joint classification and characterization of ships from SAR Sentinel-1 data. We benefit from the synergies between AIS (Automatic Identification System) and Sentinel-1 data to build significant training datasets. We design a multi-task neural network architecture composed of one joint convolutional network connected to three task specific networks, namely for ship detection, classification, and length estimation. The experimental assessment shows that our network provides promising results, with accurate classification and length performance (classification overall accuracy: 97.25%, mean length error: 4.65 m ± 8.55 m).

Download Full-text

RootNav 2.0: Deep learning for automatic navigation of complex plant root architectures

GigaScience ◽

10.1093/gigascience/giz123 ◽

2019 ◽

Vol 8 (11) ◽

Cited By ~ 14

Author(s):

Robail Yasrab ◽

Jonathan A Atkinson ◽

Darren M Wells ◽

Andrew P French ◽

Tony P Pridmore ◽

...

Keyword(s):

Neural Network ◽

Image Analysis ◽

Feature Extraction ◽

Deep Learning ◽

Transfer Learning ◽

Plant Species ◽

Network Architecture ◽

Large Scale ◽

Search Algorithm ◽

System Architectures

Abstract Background In recent years quantitative analysis of root growth has become increasingly important as a way to explore the influence of abiotic stress such as high temperature and drought on a plant's ability to take up water and nutrients. Segmentation and feature extraction of plant roots from images presents a significant computer vision challenge. Root images contain complicated structures, variations in size, background, occlusion, clutter and variation in lighting conditions. We present a new image analysis approach that provides fully automatic extraction of complex root system architectures from a range of plant species in varied imaging set-ups. Driven by modern deep-learning approaches, RootNav 2.0 replaces previously manual and semi-automatic feature extraction with an extremely deep multi-task convolutional neural network architecture. The network also locates seeds, first order and second order root tips to drive a search algorithm seeking optimal paths throughout the image, extracting accurate architectures without user interaction. Results We develop and train a novel deep network architecture to explicitly combine local pixel information with global scene information in order to accurately segment small root features across high-resolution images. The proposed method was evaluated on images of wheat (Triticum aestivum L.) from a seedling assay. Compared with semi-automatic analysis via the original RootNav tool, the proposed method demonstrated comparable accuracy, with a 10-fold increase in speed. The network was able to adapt to different plant species via transfer learning, offering similar accuracy when transferred to an Arabidopsis thaliana plate assay. A final instance of transfer learning, to images of Brassica napus from a hydroponic assay, still demonstrated good accuracy despite many fewer training images. Conclusions We present RootNav 2.0, a new approach to root image analysis driven by a deep neural network. The tool can be adapted to new image domains with a reduced number of images, and offers substantial speed improvements over semi-automatic and manual approaches. The tool outputs root architectures in the widely accepted RSML standard, for which numerous analysis packages exist (http://rootsystemml.github.io/), as well as segmentation masks compatible with other automated measurement tools. The tool will provide researchers with the ability to analyse root systems at larget scales than ever before, at a time when large scale genomic studies have made this more important than ever.

Download Full-text