neural-network

问题 I'd like to ask a general question about DNN based object detection algorithms such as Yolo, SSD or R-CNN. Assume I'd like to detect mobile phones on small images, where - consequently - the mobile devices themselves are super small, moreover, it's nearly impossible to detect them by only looking at those pixels which they appear on. For instance, looking at a 300x300 image, the mobile shows up on a 7x5 grid, so only by looking at the 7x5 picture no one can surely decide what can be seen

问题 I am creating a custom layer with weights that need to be multiplied by element-wise before activation. I can get it to work when the output and input is the same shape. The problem occurs when I have a first order array as input with a second order array as output. tensorflow.multiply supports broadcasting, but when I try to use it in Layer.call(x, self.kernel) to multiply x by the self.kernel Variable it complains that they are different shapes saying: ValueError: Dimensions must be equal,

问题 Different teams use different libraries to train and run neural networks (caffe, torch, theano...). This makes sharing difficult: each library has its own format to store networks and you have to install a new library each time you want to test other teams' work. I am looking for solutions to make this less tedious: - Is there a preferred (shared?) format to store neural networks? - Is there a service or library that can help handle different types of networks / or transform one type into

问题 I am using ConvNets to build a model to make weather forecast. My input data is 10K samples of a 96x144 matrix (which represents a geographic region) with values of a variable Z (geopotential height) in each point of the grid at a fixed height. If I include 3 different heights (Z is very different in different heights) then I have this input shape: (num_samples,96,144,3). The samples are for every hour, one sample = one hour. I have nearly 2 years of data. And the input data (Z) represents

问题 I have a neural network created using PyBrain and designed to forecast time series. I am using the sequential dataset function, and trying to use a sliding window of 5 previous values to predict the 6th. One of my problems is that I can't figure out how to create the required dataset by appending the 5 previous values to the inputs and the 6th as an output. I am also unsure of how exactly to forecast values in the series once the network is trained. Posting my code below: from pybrain

问题 I got a problem in understending the difference between MLP and SLP. I know that in the first case the MLP has more than one layer (the hidden layers) and that the neurons got a non linear activation function, like the logistic function (needed for the gradient descent). But I have read that: "if all neurons in an MLP had a linear activation function, the MLP could be replaced by a single layer of perceptrons, which can only solve linearly separable problems" I don't understand why in the

问题 I'm new to Neural Networks, and programming generally. I've written a neural network in java, and i'm looking at football data. I have two inputs: 1) Home team win % over n games 2) Away team win % over n games Using 'standard statistical models' one can predict the number of goals that will occur in a match using these two numbers alone, with a reasonable degree of accuracy. However, when i attempt to train my NN to predict the number of goals, it simply doesn't converge :( I'm using a

问题 I want to create a network where in the input layer nodes are just connected to some nodes in the next layer. Here is a small example: My solution so far is that I set the weight of the edge between i1 and h1 to zero and after every optimization step I multiply the weights with a matrix (I call this matrix mask matrix) in which every entry is 1 except the entry of the weight of the edge between i1 and h1 . (See code below) Is this approach right? Or does this have a affect on the

问题 I'm trying to to teach a neural net of 2 inputs, 4 hidden nodes (all in same layer) and 1 output node. The binary representation works fine, but I have problems with the Bipolar. I can't figure out why, but the total error will sometimes converge to the same number around 2.xx. My sigmoid is 2/(1+ exp(-x)) - 1. Perhaps I'm sigmoiding in the wrong place. For example to calculate the output error should I be comparing the sigmoided output with the expected value or with the sigmoided expected

问题 I've had a go at implementing the Nguyen Widrow algorithm (below) and it appears to function correctly, but I have some follow-on questions: Does this look like a correct implementation? Does Nguyen Widrow initialization apply to any network topology / size ? (ie 5 layer AutoEncoder) Is Nguyen Widrow initialization valid for any input range? (0/1, -1/+1, etc) Is Nguyen Widrow initialization valid for any activation function? (Ie Logistic, Tanh, Linear) The code below assumes that the network