New answers tagged

0

As you said, a CNN would be able to detect objects in different positions if the dataset contains enough examples of such cases, though the network is able to generalize and should be able to detect objects in slightly changed positions and orientations. The term "translation invariance" does not mean that translating an object in the image would ...


1

No one mentioned Planning chemical syntheses with deep neural networks and symbolic AI (published in Nature - here's arxiv link). Very impressive application of deep reinforcement learning - they use Monte Carlo Tree Search with a policy network (a-la AlphaZero) to do chemical synthesis planning. Authors claim that double blind test shown that professional ...


1

How about a Temporal Convolutional Network? It feels like for such a long sequences having the recurrent/memory based approach is not too feasible. But, intuitively, the 1D convolutions should be able to pick out those rare features from your extremely long sequences. There are also claims that TCNs are comparable to RNNs in performance on common tasks, so ...


0

Even with a binary classifier, one number does not fully represent the behaviour - the confusion matrix has three degrees of freedom. Even more with a multi-class problem, it is best to print our the whole confusion matrix. Then you can pick up problems like "large class A is well classified, many Bs are wrongly classified as C, and the few Ds are ...


1

Here is a paper that explains why ReLU rules. What we want is to disentangle data of different classes. In order to do that, we need a discontinuous mapping for the data. ReLU easily allows for that. It is even better than LeakyReLU, sigmoid and tanh in that regard. Also, the reason any of the activations work is because of the floating point error, there is ...


Top 50 recent answers are included