neural-network

问题 How exactly is an U-matrix constructed in order to visualise a self-organizing-map? More specifically, suppose that I have an output grid of 3x3 nodes (that have already been trained), how do I construct a U-matrix from this? You can e.g. assume that the neurons (and inputs) have dimension 4. I have found several resources on the web, but they are not clear or they are contradictory. For example, the original paper is full of typos. 回答1: A U-matrix is a visual representation of the distances

问题 I have two datasets listing the average voltage outputs of two assemblies of neural networks at times t, that look something like this: A = [-80.0, -80.0, -80.0, -80.0, -80.0, -80.0, -79.58, -79.55, -79.08, -78.95, -78.77, -78.45,-77.75, -77.18, -77.08, -77.18, -77.16, -76.6, -76.34, -76.35] B = [-80.0, -80.0, -80.0, -80.0, -80.0, -80.0, -78.74, -78.65, -78.08, -77.75, -77.31, -76.55, -75.55, -75.18, -75.34, -75.32, -75.43, -74.94, -74.7, -74.68] When two neural assemblies are "in phase" to a

问题 I want to create an artificial neural network (in PyBrain) that follows the following layout: However, I cannot find the proper way to achieve this. The only option that I see in the documentation is the way to create fully connected layers, which is not what I want: I want some of my input nodes to be connected to the second hidden layer and not to the first one. 回答1: The solution is to use the connection type of your choice, but with slicing parameters: inSliceFrom , inSliceTo ,

问题 I'm trying to use deep learning to predict income from 15 self reported attributes from a dating site. We're getting rather odd results, where our validation data is getting better accuracy and lower loss, than our training data. And this is consistent across different sizes of hidden layers. This is our model: for hl1 in [250, 200, 150, 100, 75, 50, 25, 15, 10, 7]: def baseline_model(): model = Sequential() model.add(Dense(hl1, input_dim=299, kernel_initializer='normal', activation='relu',

问题 I want to program a chess engine which learns to make good moves and win against other players. I've already coded a representation of the chess board and a function which outputs all possible moves. So I only need an evaluation function which says how good a given situation of the board is. Therefore, I would like to use an artificial neural network which should then evaluate a given position. The output should be a numerical value. The higher the value is, the better is the position for the

问题 In this blog post, The Unreasonable Effectiveness of Recurrent Neural Networks, Andrej Karpathy mentions future directions for neural networks based machine learning: The concept of attention is the most interesting recent architectural innovation in neural networks. [...] soft attention scheme for memory addressing is convenient because it keeps the model fully-differentiable, but unfortunately one sacrifices efficiency because everything that can be attended to is attended to (but softly).

问题 Closed. This question is off-topic. It is not currently accepting answers. Want to improve this question? Update the question so it's on-topic for Stack Overflow. Closed 4 months ago . What algorithms exist for time series forecasting/regression ? What about using neural networks ? (best docs about this topic ?) Are there python libraries/code snippets that can help ? 回答1: The classical approaches to time series regression are: auto-regressive models (there are whole literatures about them)

问题 Closed. This question is off-topic. It is not currently accepting answers. Want to improve this question? Update the question so it's on-topic for Stack Overflow. Closed 4 months ago . What algorithms exist for time series forecasting/regression ? What about using neural networks ? (best docs about this topic ?) Are there python libraries/code snippets that can help ? 回答1: The classical approaches to time series regression are: auto-regressive models (there are whole literatures about them)

问题 I am reading a lot of tutorials that state two things. "[Replacing fully connected layers with convolutional layers] casts them into fully convolutional networks that take input of any size and output classification maps." Fully Convolutional Networks for Semantic Segmentation, Shelhamer et al. A traditional CNN can't do this because it has a fully connected layer and it's shape is decided by the input image size. Based on these statements, my questions are the following? Whenever I've made a

问题 I have a neural network (NN) which works perfectly when applied to a single data set. However if I want to run the NN on, for example, one set of data and then create a new instance of the NN to run on different set of data (or even the same set again) then the new instance will produce completely incorrect predictions. For example, training on an XOR pattern: test=[[0,0],[0,1],[1,0],[1,1]] data = [[[0,0], [0]],[[0,1], [0]],[[1,0], [0]],[[1,1], [1]]] n = NN(2, 3, 1) # Create a neural network