-
Post-processing Multi-Model Medium-Term Precipitation Forecasts Using Convolu...
The dataset used in this paper is a collection of hourly precipitation forecasts from two governmental reforecasting projects operated by governmental weather services. -
ResNet-20 and ResNet-SVM-20
The dataset used in the paper is ResNet-20 and ResNet-SVM-20, two types of convolutional neural networks. -
Sales Forecast in E-commerce using Convolutional Neural Network
Sales forecast is an essential task in E-commerce and has a crucial impact on making informed business decisions. It can help us to manage the workforce, cash flow and resources... -
When is a convolutional filter easy to learn?
We consider conditions under which a single ReLU convolutional filter is learnable with gradient methods, a special case of which is a single ReLU neuron. -
UNITN: Training Deep Convolutional Neural Network for Twitter Sentiment Class...
Convolutional neural network for sentiment analysis -
CifarQuick
The CifarQuick model is a medium-sized convolutional neural network trained on the Cifar-10 dataset. -
RepBNN: towards a precise Binary Neural Network with Enhanced Feature Map via...
Binary neural network (BNN) is an extreme quantization version of convolutional neural networks (CNNs) with all features and weights mapped to just 1-bit. -
SqueezeJet: High-level Synthesis Accelerator
Deep convolutional neural networks have dominated the pattern recognition scene by providing much more accurate solutions in computer vision problems such as object recognition... -
Broadband DOA Estimation Using Convolutional Neural Networks Trained with Noi...
A convolution neural network (CNN) based classification method for broadband DOA estimation is proposed, where the phase com-ponent of the short-time Fourier transform... -
Discretised Neutron Diffusion Equation
The dataset used in this paper is a discretised neutron diffusion equation, solved using a convolutional neural network with pre-determined weights. -
pvCNN: Privacy-Preserving and Verifiable Convolutional Neural Network Testing
We propose a new approach for privacy-preserving and verifiable convolutional neural network (CNN) testing in a distrustful multi-stakeholder environment. -
Physics-informed ConvNet: Learning Physical Field from a Shallow Neural Network
The dataset used in the paper is a set of physical field observations with noisy data. -
Optimally Scheduling CNN Convolutions for Efficient Memory Access
The dataset used in this paper is a CNN convolutional layer loop-nest, which is a 6-level loop-nest representing the convolutional layer of a CNN. -
Convolution Kernel Dataset
The dataset used in this paper is a convolution kernel dataset, which is used to train and evaluate the MetaTune cost model. -
SynExp Invariance Theorem
The dataset used in the paper is not explicitly mentioned, but it is implied to be a CNN model on CIFAR-10 and ImageNet. -
Minimal Filtering Algorithms for Convolutional Neural Networks
The dataset used in this paper is a set of convolutional neural networks with small length FIR filters. -
Frequency-Aware Re-Parameterization for Over-Fitting Based Image Compression
Over-fitting based image compression requires weights compactness for compression and fast convergence for practical use, posing challenges for deep convolutional neural... -
Mixconv: Mixed depthwise convolutional kernels
The proposed method, called MixNet, mixes depthwise separable convolutions. -
EfficientNet: Rethinking model scaling for convolutional neural networks
The proposed method, called EfficientNet, rethinks model scaling for convolutional neural networks. -
Driver Distraction Identification with an Ensemble of Convolutional Neural Net...
The AUC Distracted Driver Dataset was used to evaluate the proposed approach.
