biological-neural-network

Neural network not converging

阅读更多关于 Neural network not converging

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

In NEURON .MOD files what is the order of operations of the sections?

阅读更多关于 In NEURON .MOD files what is the order of operations of the sections?

问题 In what order do the commands in NEURON .MOD/NMODL file sections get executed? Specifically, within these blocks: DERIVATIVE, BREAKPOINT and NET_RECEIVE. 回答1: For every time-step, the order of execution is as follows: NET_RECEIVE : If there is net_send() an event that targets this mechanism, lines here are executed first. Skipped otherwise. Lines in BREAKPOINT : The SOLVE ... METHOD line is ignored. All lines after SOLVE are executed. With a printf() statement, you would see two calls.

Training images and test images

阅读更多关于 Training images and test images

问题 I am working on a project about the feedforward pathway of the ventral stream, and i have 6 images to be recognized at the InferoTemporal Layer. Please can someone give me images' exmamples showing to me what is the difference between training images and test images. So what i should add to my folder that contain my training images? Does i should add another folder that contain a list of test images ? if yes, what should be these test images? Does the training images must contains the images

High training error at the beginning of training a Convolutional neural network

阅读更多关于 High training error at the beginning of training a Convolutional neural network

问题 In the Convolutional neural network, I'm working on training a CNN, and during the training process, especially at the beginning of my training I get extremely high training error. After that, this error starts to go down slowly. After approximately 500 Epochs the training error comes near to zero (e.g. 0.006604). Then, I took the final obtained model to measure its accuracy against the testing data, I've got about 89.50%. Does that seem normal? I mean getting a high training error rate at

Calculating convolution of two functions using FFT (FFTW)

阅读更多关于 Calculating convolution of two functions using FFT (FFTW)

问题 I'm trying to speed up a computation for a neural simulator using the FFT. The equation is: (1) \sum(j=1 to N) (w(i - j) * s_NMDA[j]) where s_NMDA is a vector of length N and w is defined by: (2) w(j) = tanh[1/(2 * sigma * p)] * exp(-abs(j) / (sigma * p)] where sigma and p are constants. (is there a better way to render equations on stackoverflow?) The calculation has to be done for N neurons. Since (1) only depends on the absolute distance abs(i - j), it should be possible to compute this

Neural network not converging

阅读更多关于 Neural network not converging

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 genetic algorithm to train the network, here is the fittest individual from the first few generations with a

Brain modelling

阅读更多关于 Brain modelling

问题 Just wondering, since we've reached 1 teraflop per PC, yet we are still not able to model an insect's brain. Has anyone seen a decent implementation of a self-learning, self-developing neural network? 回答1: I saw an interesting experiment mapping the physical neural layout of a rat's brain to a digital neural network with weighting modelled on the neuron chemistry of each component taken using MRI and others. Quite interesting. (new scientist or Focus, 2 issues ago?) IBM Blue Brain comes to

Spiking neural networks

阅读更多关于 Spiking neural networks

Which is the book one should start with in the domain of spiking neural networks? I know about Gerstner's "Spiking Neuron Models" , published in 2002. Is there a more recent book, or maybe a more suitable one? I have a background in maths and artificial neural networks. If there are some good articles or overviews in this domain, also add them to the list. Thanks. LATER EDIT Karel's answer: " It depends what do you mean by spiking neural networks - there are at least several basic points of view. Gerstner represents the first one - he is focused on modelling of biological neurons. And his book

Spiking neural networks

阅读更多关于 Spiking neural networks

问题 Which is the book one should start with in the domain of spiking neural networks? I know about Gerstner's "Spiking Neuron Models", published in 2002. Is there a more recent book, or maybe a more suitable one? I have a background in maths and artificial neural networks. If there are some good articles or overviews in this domain, also add them to the list. Thanks. LATER EDIT Karel's answer: " It depends what do you mean by spiking neural networks - there are at least several basic points of