Search · four archives
Search · four archives
24 papers · ranked by Valyu relevance
Aran Nayebi, Daniel M. Bear, Jonas Kubilius, Kohitij Kar + 4 more
'Surya Ganguli' 'David Sussillo' 'James J. DiCarlo' 'Daniel Yamins'] Feed-forward convolutional neural networks (CNNs) are currently state-of-the-art for object classification tasks such as ImageNet. Further, they are quantitatively accurate models of temporally-averaged responses of neurons in the primate brain's…
Gil Keren, Björn W. Schuller
—Traditional convolutional layers extract features from patches of data by applying a non-linearity on an affine function of the input. We propose a model that enhances this feature extraction process for the case of sequential data, by feeding patches of the data into a recurrent neural network and using the outputs…
Yajing Zheng, Shanshan Jia, Zhaofei Yu, Jian K. Liu + 1 more
Title: Summary Traditional models of retinal system identification analyze the neural response to artificial stimuli using models consisting of predefined components. The model design is limited to prior knowledge, and the artificial stimuli are too simple to be compared with stimuli processed by the retina. To fill in…
Courtney J. Spoerer, Patrick McClure, Nikolaus Kriegeskorte
Feedforward neural networks provide the dominant model of how the brain performs visual object recognition. However, these networks lack the lateral and feedback connections, and the resulting recurrent neuronal dynamics, of the ventral visual pathway in the human and nonhuman primate brain. Here we investigate…
Yannan Xing, Gaetano Di Caterina, John Soraghan
The combination of neuromorphic visual sensors and spiking neural network offers a high efficient bio-inspired solution to real-world applications. However, processing event- based sequences remains challenging because of the nature of their asynchronism and sparsity behavior. In this paper, a novel spiking…
Francesco Visin, Kyle Kastner, Kyunghyun Cho, Matteo Matteucci + 2 more
'Aaron Courville' 'Yoshua Bengio'] In this paper, we propose a deep neural network architecture for object recognition based on recurrent neural networks. The proposed network, called ReNet, replaces the ubiquitous convolution+pooling layer of the deep convolutional neural network with four recurrent neural networks…
Jianfeng Wang, Xiaolin Hu
—The convolutional neural network (CNN) has become a basic model for solving many computer vision problems. In recent years, a new class of CNNs, recurrent convolution neural network (RCNN), inspired by abundant recurrent connections in the visual systems of animals, was proposed. The critical element of RCNN is the…
Pengfei Meng, Shuangcheng Jia, Qian Li
Sequence recognition of natural scene images has always been an important research topic in the field of computer vision. CRNN has been proven to be a popular end-to-end character sequence recognition network. However, the problem of wide characters is not considered under the setting of CRNN. The CRNN is less…
Aran Nayebi, Javier Sagastuy-Brena, Daniel M. Bear, Kohitij Kar + 5 more
The ventral visual stream (VVS) is a hierarchically connected series of cortical areas known to underlie core object recognition behaviors, enabling humans and non-human primates to effortlessly recognize objects across a multitude of viewing conditions. While recent feedforward convolutional neural networks (CNNs)…
Courtney J. Spoerer, Tim C. Kietzmann, Johannes Mehrer, Ian Charest + 2 more
'Nikolaus Kriegeskorte' 'Leyla Isik'] Deep feedforward neural network models of vision dominate in both computational neuroscience and engineering. The primate visual system, by contrast, contains abundant recurrent connections. Recurrent signal flow enables recycling of limited computational resources over time, and…
Courtney J Spoerer, Tim C Kietzmann, Johannes Mehrer, Ian Charest + 1 more
Deep feedforward neural network models of vision dominate in both computational neuroscience and engineering. The primate visual system, by contrast, contains abundant recurrent connections. Recurrent signal flow enables recycling of limited computational resources over time, and so might boost the performance of a…
Fangzhou Liao, Xiaolin Hu, Sen Song
The connectivity pattern and function of the recurrent connections in the primary visual cortex (V1) have been studied for a long time. But the underlying mechanism remains elusive. We hypothesize that the recurrent connectivity is a result of performance optimization in recognizing images. To test this idea, we added…
Jessica Loke, Noor Seijdel, Lukas Snoek, Matthew van der Meer + 4 more
Recurrent processing is a crucial feature in human visual processing supporting perceptual grouping, figure-ground segmentation, and recognition under challenging conditions. There is a clear need to incorporate recurrent processing in deep convolutional neural networks (DCNNs) but the computations underlying recurrent…
Jithendar Anumula, Daniel Neil, Tobi Delbruck, Shih-Chii Liu
Event-driven neuromorphic spiking sensors such as the silicon retina and the silicon cochlea encode the external sensory stimuli as asynchronous streams of spikes across different channels or pixels. Combining state-of-art deep neural networks with the asynchronous outputs of these sensors has produced encouraging…
Authors not listed
The automatic generation of image captions in natural language is a critical and challenging task, particularly in the context of environmental monitoring and control. This paper presents a novel deep learning-driven image captioning system designed for real-time monitoring and predictive control of pollutant gas…
Jian-wei Liu, Bingrong Xu, Zhiyan Song
Recursive and recurrent neural networks are the main realization forms of sequence models based on neural networks, which have been developed rapidly in recent years. Recurrent neural networks are basically standard processing methods for machine translation, question and answer, and sequence video analysis. It is also…
Authors not listed
Obtaining quantitative information about residence time behavior (i.e., the residence time distribution function) in realistic experimental systems is oftentimes experimentally challenging and numerically complex. The conventional way is to conduct very simple pulse or step tracer experiments or construct elaborate…
Sukhdeep Singh, Sudhir Rohilla, Anuj Sharma
handwriting recognition Authors: ['Sukhdeep Singh' 'Sudhir Rohilla' 'Anuj Sharma'] Deep learning expresses a category of machine learning algorithms that have the capability to combine raw inputs into intermediate features layers. These deep learning algorithms have demonstrated great results in different fields. Deep…
Authors not listed
This research presents a novel approach to obstacle detection during navigation using a combination of Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks. The primary objective is to generate accurate image captions that describe the content of images, which is crucial for applications such…
Chuang Liu, Yang Chen, Chang Seok Bang
Spiking neural networks (SNNs) have emerged as a promising paradigm for energy-efficient neuromorphic computing, particularly when processing asynchronous event streams from dynamic vision sensors (DVSs). However, SNNs often suffer from limited representational capacity and suboptimal feature recalibration compared to…
Sweta Kumari, C Vigneswaran, V. Srinivasa Chakravarthy
Sequential decision making tasks that require information integration over extended durations of time are challenging for several reasons including the problem of vanishing gradients, long training times and significant memory requirements. To this end we propose a neuron model fashioned after the JK flip-flops in…
Chenxi Sui, Ziyang Jiang, Genesis Higueros, David Carlson + 1 more
High-performance batteries are poised for electrification of vehicles and therefore mitigate greenhouse gas emissions, which, in turn, promote a sustainable future. However, the design of optimized batteries is challenging due to the nonlinear governing physics and electrochemistry. Recent advancements have…
Sanjar Adilov
Generative neural networks have shown promising results in de novo drug design. Recent studies suggest that one of the efficient ways to produce novel molecules matching target properties is to model SMILES sequences using deep learning in a way similar to language modeling in natural language processing. In this…
Rongpei Gou, Jingyi Yang, Menghan Guo, Yingjun Chen + 1 more
Central nervous system (CNS) drugs have had a significant impact on human health, e.g., treating a wide range of neurodegenerative and psychiatric disorders. In recent years, deep learning-based generative models, particularly those for designing drugs from scratch, have shown great potential for accelerating drug…