New answers tagged

0

The wiki has a concise quote by Andreas Hein, where the gap is defined by "the difference in meaning between constructs formed within different representation systems". This connotes the core problem of translating meaning between an informal language (typically natural language) and a formal language (programing language or other formal symbolic ...


4

Statistical efficiency in this context essentially means that a CNN would require fewer training examples than a fully connected network to learn. Intuitively this seems reasonable: more parameters to learn should mean more samples needed. Of course it is always desirable to minimise the number of training samples needed, so that's a definite advantage of ...


4

In terms of transfer learning, semantic gap means different meanings and purposes behind the same syntax between two or more domains. For example, suppose that we have a deep learning application to detect and label a sequence of actions/words $a_1, a_2, \ldots, a_n$ in a video/text as a "greeting" in a society A. However, this knowledge in Society ...


0

Recently, I've been thinking this question as well. After reading several papers, finally came up with some thoughts about the surrogate model. In FEM(finite element method), we try to find a weak form to approximate the strong form so that we can solve the weak form analytically. (weak form: approximation equation; strong form: PDE in real world) In my ...


3

Yes, it is not unusual to omit the bias by adding a neuron which always outputs a constant 1, which will then be multiplied by an appropriate weight to give the same formula as you would get using an explicit bias. One notable text using this convention is Understanding Machine Learning: From Theory to Algorithms by Shai Shalev-Shwartz and Shai Ben-David. ...


2

Not quite sure about RNN & LSTM (and it always depends on the task), but for CNN the answer is clearly no; CNN routinely include FC layers. Quoting from the highly popular (and recommended) Stanford course CS231n: Convolutional Neural Networks for Visual Recognition: ConvNet Architectures We have seen that Convolutional Networks are commonly made up of ...


0

$\mathcal S$ is just a set of all possible states. It doesn't matter if it's agents perceived state or true environment state, they are within the same set of states. Agent cannot perceive itself to be in some "middle" state that's not in $\mathcal S$, it might think that's in the state that's not the actual environment state but that state is also ...


Top 50 recent answers are included