Auto Topic: convolutional
auto_convolutional | topic
Coverage Score
1
Mentioned Chunks
55
Mentioned Docs
1
Required Dimensions
definitionpros_cons
Covered Dimensions
definitionpros_cons
Keywords
convolutional
Relations
| Source | Type | Target | W |
|---|---|---|---|
| Auto Topic: convolutional | CO_OCCURS | Propositional Logic | 10 |
| Auto Topic: convolutional | CO_OCCURS | Auto Topic: pixels | 7 |
| Auto Topic: cnn | CO_OCCURS | Auto Topic: convolutional | 7 |
| Auto Topic: convolutional | CO_OCCURS | Auto Topic: spatial | 6 |
| Auto Topic: convolution | CO_OCCURS | Auto Topic: convolutional | 6 |
| Auto Topic: convolutional | CO_OCCURS | State-Space Search | 5 |
| Auto Topic: convolutional | CO_OCCURS | Auto Topic: kernel | 5 |
| Auto Topic: convolutional | CO_OCCURS | Auto Topic: relu | 5 |
| Auto Topic: activation | CO_OCCURS | Auto Topic: convolutional | 5 |
| Auto Topic: convolutional | CO_OCCURS | Constraint Satisfaction Problem | 4 |
| Auto Topic: cnns | CO_OCCURS | Auto Topic: convolutional | 4 |
| Auto Topic: convolutional | CO_OCCURS | Auto Topic: dimension | 3 |
| Auto Topic: convolutional | CO_OCCURS | Auto Topic: residual | 3 |
| Auto Topic: convolutional | CO_OCCURS | Auto Topic: scene | 3 |
| Auto Topic: convolutional | CO_OCCURS | Auto Topic: window | 3 |
| Auto Topic: convolutional | CO_OCCURS | Logical Agents | 3 |
| Auto Topic: convolutional | CO_OCCURS | Auto Topic: detector | 3 |
| Auto Topic: conference | CO_OCCURS | Auto Topic: convolutional | 3 |
Evidence Chunks
| Source | Confidence | Mentions | Snippet |
|---|---|---|---|
textbook Artificial-Intelligence-A-Modern-Approach-4th-Edition.pdf | 0.59 | 3 | ... egs. Modern methods deal with these problems by learning representations and classifiers from very large quantities of training data using a convolutional neural network. With a sufficiently rich training set the classifier will have seen any effect of importance many times in train ... |
textbook Artificial-Intelligence-A-Modern-Approach-4th-Edition.pdf | 0.59 | 3 | e effect. 27.4.1 Image classification with convolutional neural networks Convolutional neural networks (CNNs)are spectacularly successful image classifiers. With enough training data and enough training ingenuity, CNNs produce very successful classifi- cation systems, much better th ... |
textbook Artificial-Intelligence-A-Modern-Approach-4th-Edition.pdf | 0.57 | 2 | ... ls that facilitate rapid exploration and evaluation of different structures are essential for success in real-world problems. Section 22.3 Convolutional Networks 811 22.3 Convolutional Networks We mentioned in Section 22.2.1 that an image cannot be thought of as a simple vector o ... |
textbook Artificial-Intelligence-A-Modern-Approach-4th-Edition.pdf | 0.57 | 2 | ... mely, knowledge of adjacency and spatial invariance—we can develop models that have far fewer parameters and can learn much more quickly. A convolutional neural network (CNN)is one that contains spatially local connections, Convolutional neural network (CNN) at least in the early ... |
textbook Artificial-Intelligence-A-Modern-Approach-4th-Edition.pdf | 0.57 | 2 | rameters and can learn much more quickly. A convolutional neural network (CNN)is one that contains spatially local connections, Convolutional neural network (CNN) at least in the early layers, and has patterns of weights that are replicated across the units in each layer. A patte ... |
textbook Artificial-Intelligence-A-Modern-Approach-4th-Edition.pdf | 0.57 | 2 | ... that the same update rule is useful at all points in a stream of sequential data. To the extent that these assumptions are valid, we expect convolutional architectures to generalize well on images and recurrent networks to generalize well on text and audio signals. 6 Noting that ... |
textbook Artificial-Intelligence-A-Modern-Approach-4th-Edition.pdf | 0.57 | 2 | ... capacity to function as lookup tables for the training data. The last piece of the puzzle, at least for vision applications, was the use of convolutional networks. These had their origins in the descriptions of the mammalian visual system by neurophysiologists David Hubel and Tor ... |
textbook Artificial-Intelligence-A-Modern-Approach-4th-Edition.pdf | 0.57 | 2 | ... Poggio, 1976). The neocognitron (Fukushima, 1980; Fukushima and Miyake, 1982), designed as a model of the visual cortex, was essentially a convolutional network in terms of model architecture, although an effective training algorithm for such networks had to wait until Yann LeCu ... |
textbook Artificial-Intelligence-A-Modern-Approach-4th-Edition.pdf | 0.57 | 2 | Net competition in 2010, systems could do no better than 70% top-5 accuracy. The introduction of convolutional neural networks in 2012 and their subsequent refinement led to an accuracy of 98% in top-5 (surpassing human performance) and 87% in top-1 accuracy by 2019. The primary r ... |
textbook Artificial-Intelligence-A-Modern-Approach-4th-Edition.pdf | 0.57 | 2 | ... lized neighborhoods; then other features look at patterns of those features; then others look at patterns of those, and so on. This is what convolutional neural networks do well. You should think of a layer—a con- volution followed by a ReLU activation function—as a local pattern ... |
textbook Artificial-Intelligence-A-Modern-Approach-4th-Edition.pdf | 0.57 | 2 | ... ad alternating layers of simple cells and complex cells, thus incorporating downsampling, and also had shift invariance, thus incorporating convolutional structure. LeCun et al. (1989) took the additional step of using back-propagation to train the weights of this network, and wh ... |
textbook Artificial-Intelligence-A-Modern-Approach-4th-Edition.pdf | 0.57 | 2 | ... g based recommender system: A survey and new per- spectives. arXiv:1707.07435. Zhang, X., Zhao, J., and LeCun, Y . (2016). Character- level convolutional networks for text classification. In NeurIPS 28. Zhang, Y ., Pezeshki, M., Brakel, P., Zhang, S., Lau- rent, C., Bengio, Y ., a ... |
textbook Artificial-Intelligence-A-Modern-Approach-4th-Edition.pdf | 0.55 | 1 | ... ks . . . . . . . . . . . . . . . . . . . . . . . 802 22.2 Computation Graphs for Deep Learning . . . . . . . . . . . . . . . . . . 807 22.3 Convolutional Networks . . . . . . . . . . . . . . . . . . . . . . . . . . . 811 22.4 Learning Algorithms . . . . . . . . . . . . . . . . . ... |
textbook Artificial-Intelligence-A-Modern-Approach-4th-Edition.pdf | 0.55 | 1 | ... e, adjustableDeep learning computing elements. Experiments were carried out with such networks as far back as the 1970s, and in the form of convolutional neural networks they found some success in hand- written digit recognition in the 1990s (LeCun et al., 1995). It was not until ... |
textbook Artificial-Intelligence-A-Modern-Approach-4th-Edition.pdf | 0.55 | 1 | ... he number of nodes. The data is from a version of the restaurant problem. The optimal size is 7. In (b) the model class is convolutional neural networks (see Section 22.3) and the hyperparameter is the number of regular parameters in the network. The data is the MNIST data set of ... |
textbook Artificial-Intelligence-A-Modern-Approach-4th-Edition.pdf | 0.55 | 1 | ... picture as dog, if we tried to interpret the model directly, the best we could come away with would be something like “after processing the convolutional layers, the activation for the dog output in the softmax layer was higher than any other class.” That’s not a very compelling ... |
textbook Artificial-Intelligence-A-Modern-Approach-4th-Edition.pdf | 0.55 | 1 | ... such networks. Section 22.2 goes into more detail on how deep networks are put together, and Section 22.3 covers a class of networks called convolutional neural networks that are especially important in vision applications. Sections 22.4 |
textbook Artificial-Intelligence-A-Modern-Approach-4th-Edition.pdf | 0.55 | 1 | more detail on how deep networks are put together, and Section 22.3 covers a class of networks called convolutional neural networks that are especially important in vision applications. Sections 22.4 and 22.5 go into more detail on algorithms for training networks from data and m ... |