biological-neural-network

Neural network not converging

狂风中的少年 提交于 2020-01-02 19:30:34
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?

断了今生、忘了曾经 提交于 2019-12-25 06:48:09
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

假装没事ソ 提交于 2019-12-23 03:59:08
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

旧巷老猫 提交于 2019-12-13 01:09:27
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)

非 Y 不嫁゛ 提交于 2019-12-09 07:16:09
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

蹲街弑〆低调 提交于 2019-12-06 07:54:56
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

时间秒杀一切 提交于 2019-12-03 12:57:52
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

无人久伴 提交于 2019-11-30 07:33:49
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

☆樱花仙子☆ 提交于 2019-11-29 09:59:50
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