합성곱 신경망

노트

위키데이터

• ID : Q17084460

말뭉치

1. ConvNet architectures make the explicit assumption that the inputs are images, which allows us to encode certain properties into the architecture.
2. A ConvNet arranges its neurons in three dimensions (width, height, depth), as visualized in one of the layers.
3. A ConvNet is made up of Layers.
4. We use three main types of layers to build ConvNet architectures: Convolutional Layer, Pooling Layer, and Fully-Connected Layer (exactly as seen in regular Neural Networks).
5. The final layer of the CNN architecture uses a classification layer such as softmax to provide the classification output.
6. This tutorial demonstrates training a simple Convolutional Neural Network (CNN) to classify CIFAR images.
7. As input, a CNN takes tensors of shape (image_height, image_width, color_channels), ignoring the batch size.
8. In this example, you will configure our CNN to process inputs of shape (32, 32, 3), which is the format of CIFAR images.
9. Why ReLU is important : ReLU’s purpose is to introduce non-linearity in our ConvNet.
10. The pre-processing required in a ConvNet is much lower as compared to other classification algorithms.
11. The architecture of a ConvNet is analogous to that of the connectivity pattern of Neurons in the Human Brain and was inspired by the organization of the Visual Cortex.
12. A ConvNet is able to successfully capture the Spatial and Temporal dependencies in an image through the application of relevant filters.
13. The role of the ConvNet is to reduce the images into a form which is easier to process, without losing features which are critical for getting a good prediction.
14. CNN is a class of deep learning networks that has attracted much attention in recent studies.
15. At the beginning of the application of CNN, a similar pipeline is adopted as in the supervised learning models, except that the machine learning algorithms are replaced by CNN.
16. The pipeline of CNN-based models is illustrated in Fig.
17. Illustration of CNN-based model.
18. As shown, it is necessary to prepare a large number of training data with corresponding labels for efficient classification using CNN.
19. They used a multiview strategy in 3D-CNN, whose inputs were obtained by cropping three 3D patches of a lung nodule in different sizes and then resizing them into the same size.
20. To utilize time series data, the study used triphasic CT images as 2D images with three channels, which corresponds to the RGB color channels in computer vision, for 2D-CNN.
21. However, one can also apply CNN to this task as well.
22. Central to the convolutional neural network is the convolutional layer that gives the network its name.
23. In the context of a convolutional neural network, a convolution is a linear operation that involves the multiplication of a set of weights with the input, much like a traditional neural network.
24. The name “convolutional neural network” indicates that the network employs a mathematical operation called convolution.
25. A convolutional neural network consists of an input and an output layer, as well as multiple hidden layers.
26. The hidden layers of a CNN typically consist of a series of convolutional layers that convolve with a multiplication or other dot product.
27. The neocognitron is the first CNN which requires units located at multiple network positions to have shared weights.
28. To start, the CNN receives an input feature map: a three-dimensional matrix where the size of the first two dimensions corresponds to the length and width of the images in pixels.
29. For each filter-tile pair, the CNN performs element-wise multiplication of the filter matrix and the tile matrix, and then sums all the elements of the resulting matrix to get a single value.
30. During training, the CNN "learns" the optimal values for the filter matrices that enable it to extract meaningful features (textures, edges, shapes) from the input feature map.
31. As the number of filters (output feature map depth) applied to the input increases, so does the number of features the CNN can extract.
32. These operations are the basic building blocks of every Convolutional Neural Network, so understanding how these work is an important step to developing a sound understanding of ConvNets.
33. The primary purpose of Convolution in case of a ConvNet is to extract features from the input image.
34. It is important to understand that these layers are the basic building blocks of any CNN.
35. Please note however, that these operations can be repeated any number of times in a single ConvNet.
36. Deep CNN made a noteworthy contribution in several domains like image classification and recognition; therefore, they become widely known standards.
37. This section describes various classical and modern architectures of Deep CNN, which are currently utilized as a building block of several segmentation architectures.
38. This CNN model implements dropout layers with a particular end goal to battle the issue of overfitting to the training data.
39. The controller is a predefined RNN, where child model is the required CNN for classification of images.