Add to ORKGInternational audienceComputational complexity of Convolutional Neural Networks (CNNs) makes its integration in embedded systems a challenging task. Methods allowing to simplify these algorithms are therefore of great interest. In this paper, we propose a new CNN compression method based on the application of Principal Component Analysis (PCA) in a layer-wise fashion, and show the benefits of an additional fine-tuning step. Through this method, it is possible to reach very flexible trade-offs between network size and accuracy, such as a x2 reduction in the number of parameters for an accuracy drop inferior to 2%. We also discuss its compatibility with other well-known CNN compression methods
This paper presents a new method for image compression by neural networks. First, we show that we ca...
Classical feature extraction and data projection methods have been extensively investigated in the p...
Hardware-efficient CNN model design can be divided into two stages: training of a large baseline net...
Deep convolutional neural networks (CNNs) generate intensive inter-layer data during inference, whic...
Convolutional Neural Networks (CNNs) are brain-inspired computational models designed to recognize p...
We present a method to adaptively combine multilayer perceptrons and vector quantization. We show th...
Convolutional Neural Networks (CNNs) were created for image classification tasks. Quickly, they were...
PCANet is an unsupervised Convolutional Neural Network (CNN), which uses Principal Component Analysi...
Convolutional neural networks (CNNs) were created for image classification tasks. Shortly after thei...
Convolutional neural networks (CNNs) offer significant advantages when used in various image classif...
In this paper we consider Principal Component Analysis (PCA) and Vector Quantization (VQ) neural net...
Local Principal Components Analysis, i.e. Principal Component Analysis performed in data clusters, i...
Dimensionality reduction is the search for a low-dimensional space that captures the 'essence' of th...
Deep convolutional neural networks (CNNs) have been successful in many tasks in machine vision, howe...
Convolutional neural networks (CNNs) were created for image classification tasks. Shortly after thei...
This paper presents a new method for image compression by neural networks. First, we show that we ca...
Classical feature extraction and data projection methods have been extensively investigated in the p...
Hardware-efficient CNN model design can be divided into two stages: training of a large baseline net...
Deep convolutional neural networks (CNNs) generate intensive inter-layer data during inference, whic...
Convolutional Neural Networks (CNNs) are brain-inspired computational models designed to recognize p...
We present a method to adaptively combine multilayer perceptrons and vector quantization. We show th...
Convolutional Neural Networks (CNNs) were created for image classification tasks. Quickly, they were...
PCANet is an unsupervised Convolutional Neural Network (CNN), which uses Principal Component Analysi...
Convolutional neural networks (CNNs) were created for image classification tasks. Shortly after thei...
Convolutional neural networks (CNNs) offer significant advantages when used in various image classif...
In this paper we consider Principal Component Analysis (PCA) and Vector Quantization (VQ) neural net...
Local Principal Components Analysis, i.e. Principal Component Analysis performed in data clusters, i...
Dimensionality reduction is the search for a low-dimensional space that captures the 'essence' of th...
Deep convolutional neural networks (CNNs) have been successful in many tasks in machine vision, howe...
Convolutional neural networks (CNNs) were created for image classification tasks. Shortly after thei...
This paper presents a new method for image compression by neural networks. First, we show that we ca...
Classical feature extraction and data projection methods have been extensively investigated in the p...
Hardware-efficient CNN model design can be divided into two stages: training of a large baseline net...