The handbook of brain theory and neural networks

By Lalit M. Patnaik. 2013

148 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Efficient Defenses Against Adversarial Attacks (2017, methodology): “Notice that CNN + BRELU performs best for a distortion of up to (cid:15) = 0 .”
Quantum-chemical insights from deep tensor neural networks (2016, methodology): “The factor representation in the presented models employs 60 neurons.”
Phone recognition with hierarchical convolutional deep maxout networks (2015, background): “In fact, CNNs have been successfully used in image processing for a long time (including early efforts at modelling speech [2]), but their applicability to speech recognition had not thoroughly been explored before the current renaissance of artificial neural networks.”
Deep Learning in Medical Imaging: General Overview (2017, background): “Recently, ensemble learning, combined with the diverse classification algorithm for precise prediction, is commonly being used for more advanced classifications (7).”
Deep Learning With Spiking Neurons: Opportunities and Challenges (2018, background): “Our definition includes multi-layer fully-connected networks, convolutional neural networks (CNNs; LeCun and Bengio, 1995), deep belief networks (DBNs; Hinton et al.”
Efficiently Trainable Text-to-Speech System Based on Deep Convolutional Networks with Guided Attention (2017, methodology): “In this paper, we denote the 1D convolution layer [30] by a space saving notation Co←i k?δ (X), where i is the size of input channel, o is the size of output channel, k is the size of kernel, δ is the dilation factor, and an argumentX is a tensor having three dimensions (batch, channel, temporal).”
Sketch-based 3D shape retrieval using Convolutional Neural Networks (2015, methodology): “Specifically, we use two different networks to handle sources from different domains.”
Multi-Speaker DOA Estimation Using Deep Convolutional Networks Trained With Noise Signals (2018, background): “work, where the architecture typically consists of one or more convolution layers followed by fully-connected networks leading ot the output [29].”
Language Model Pre-training for Hierarchical Document Representations (2019, unknown): “Common choices for the representation modules are LSTMs, CNNs, and self-attention architectures (Hochreiter & Schmidhuber, 1997; LeCun & Bengio, 1998; Vaswani et al., 2017).”
Toward embedded detection of polyps in WCE images for early diagnosis of colorectal cancer (2014, methodology): “sification were compared: learning vector quantization technique (LVQ) [19], classic Adaboost, and finally attentional boosting (Cascade Adaboost).”
Graph-Based Classification of Omnidirectional Images (2017, background): “One example of such standard techniques are the Convolutional Neural Networks (ConvNets) [8], which are primarily designed for regular domains [9].”