In machine learning and cognitive science, neural networks are a family of statistical learning models inspired by biological neural networks and are used to estimate or approximate functions that can depend on a large number of inputs and are generally unknown.
3
votes
1answer
37 views
A simple fully connected ANN module
I've written a simple module that creates a fully connected neural network of any size. The arguments of the train function are list of tuples with a training example array first and an array ...
9
votes
1answer
277 views
Neural Network in Haskell
Following this website I wrote a neural network which uses the MNIST training data to recognize digits. The author writes that it should take a couple of minutes to train the network with 30 epochs of ...
1
vote
1answer
76 views
Neural net in C++
I wrote a Matrix struct and a neural net that uses it. Why is this slow? Gprof blames Matrix::operator()(int, int) which I ...
7
votes
1answer
96 views
A CNN in Python WITHOUT frameworks
Here's some code that I've written for implementing a Convolutional Neural Network for recognising handwritten digits from the MNIST dataset over the last two days (after a lot of research into ...
3
votes
1answer
89 views
Different neural network activation functions and gradient descent
I've implemented a bunch of activation functions for neural networks, and I just want have validation that they work correctly mathematically. I implemented sigmoid, tanh, relu, arctan, step function, ...
3
votes
1answer
86 views
Implementing the Barabási–Albert model
I am writing a code for Barabási–Albert(BA) model with specific node and edges.
The algorithm is almost like [1] as follows:
...
3
votes
2answers
95 views
Assembling edges of a graph
I'm making a neural network that comprises five populations of feature-selective neurons and one population of non-selective neurons. Each neuron in this network receives connections from
c * f * ...
1
vote
0answers
36 views
Self organizing maps
I have already asked similar question here, but I figured this place might be better on getting some actual implementation feedback.
I tried to implement a simple SOM. You can see the training ...
0
votes
0answers
77 views
Theano code for 2-layer neural net for mnist
I did not attach the data, but it is the standard mnist in CSV format. I am new to theano, and I would like comments on the implementation of this code, as well as suggestions on better code-writing.
...
3
votes
1answer
108 views
3
votes
1answer
105 views
Representation of an artificial neuron
I have started to interest myself in artificial intelligence a while ago, especially within the game industry. I have started with state machines moved on to fuzzy logic and now I want to learn and ...
8
votes
2answers
733 views
Conversion of a simple Python Neural Network to a Haskell implementation
I started with this code and modified and expanded it in Python. As an exercise/challenge to myself I decided to covert the original to Haskell. I either write imperatively or functionally. This is ...
3
votes
2answers
104 views
3-level deep if-else tree for constructing a neural network
The following code fragment constructs different types of neural networks outputs based on the options supplied. Currently, my code just has a huge note that describes what all the options are ...
3
votes
0answers
103 views
Logistic regression with eigen
I am a new to Eigen, and I implemented a logistic regression model with it. It works but I don't know whether it is implemented in an efficient way.
...
3
votes
1answer
118 views
Simple neural-network simulation in C++ (Round 4)
You may want to take a look at Rounds 1, 2, and 3, though that isn't necessary for understanding what's below.
The major change since Round 3 is that my code is much cleaner and I'm including ...
0
votes
0answers
47 views
Perceptron with 2 output neurons and binary input
To the best of my knowledge I've implemented a functional version of the perceptron algorithm, but as my knowledge is not so developed as of yet I'm wondering if I've done it correctly or not.
What ...
1
vote
1answer
70 views
Neural Net XOR Genetic Algorithms
New to Neural Networks and before I move on to gradient descent I would like to make sure I have got basic idea right. (Sorry that the class is called perceptron I know that this isnt technically ...
3
votes
1answer
109 views
Simple neural-network simulation in C++ (Round 3)
As I mentioned at the end of my Round 2 answer, I've needed to expand my code in order to produce faithfully the data needed for Figure 1 of this paper.
Unfortunately, the updates have made my script ...
3
votes
1answer
147 views
Simple neural-network simulation in C++ (Round 2)
Intro
Yesterday I posted this question. Since then, I've updated my code to incorporate these suggestions. I've also removed the dependence on C++11. Finally, I've made the following changes that ...
4
votes
1answer
349 views
Simple neural-network simulation in C++
The C++ code below simulates the timecourse of the membrane potential (V) of a population of 128 leaky integrate-and-fire ...
3
votes
1answer
46 views
Finding the max error of a set of training data
I wrote a neural net, and a Trainer class that automates training the net using a training set; a set of input, and the expected output value.
Originally, I was ...
2
votes
1answer
51 views
Randomly learning a neuron to act as a signal counter
I have this small program for learning an artificial neuron to act as a simple signal counter: my cell has four input wires (also called dendrites) and a single output wire (also called axon). If at ...
6
votes
1answer
162 views
CUDA Kernel - Neural Net
I'm building a spiking neural net (recurrent, integrate and fire), and I'm curious about how to reduce the warp divergence (and other problems) I may have.
Here's an example with a few hand-placed ...
10
votes
1answer
2k views
Layered Neural Network in Swift
I am designing a very basic layered neural network in Swift as an exercise. I currently got the network evaluating the response for a given stimulus by propagating the stimulus forwards through the ...
6
votes
2answers
414 views
Simple Java Neural Network
I've written a toy neural network in Java. I ran it several million times with the same outputs with only the randomized weights changing from run to run. The average of all of the outputs is not 0.5, ...
11
votes
1answer
313 views
Backpropagating with Neural Network
I wrote a Java program implementing a neural network with backpropagation. For anyone who isn't familiar with Neural Networks and Backpropagation, here is a good resource. Here is another ...
64
votes
1answer
2k views
Siamese neural network
I have been studying the architecture of the Siamese neural network introduced by Yann LeCun and his colleagues in 1994 for the recognition of signatures ("Signature verification using a Siamese time ...
8
votes
1answer
226 views
Artificial Neural Network implementaion
I'm looking for some general tips on code practices, doing things properly in idiomatic pythonic way. But mostly I want to know if this was build correctly. I tried making neural nets in the past, but ...
4
votes
1answer
230 views
Neural Network Simulator with OpenMP
I wrote a simple neural network simulator (the biophysical kind) from scratch, and was hoping to get some feedback on how I can speed things up, or any C++ / compilation best practices that I can ...
7
votes
1answer
596 views
Simple Hopfield Network pattern recall
Here is a simple Hopfield network that I wrote with the help of a book that I am reading. I would like you to review it and give me your suggestions, especially for the node-updating part (the last ...
3
votes
1answer
143 views
Neural Network in Julia
I am currently trying to implement a Neural Net in Julia with the goal of eventually implementing a stacked autoencoder. My code seems to work but I would appreciate any constructive criticism. If ...
11
votes
2answers
861 views
Neural Network appears to be slow
I have some neural network Julia code which I'm hoping to speed up. It's possibly simply poorly-designed, but I'm not convinced.
...
11
votes
1answer
2k views
Clojure Neural Network
After reading this article about Neural Networks I was inspired to write my own implementation that allows for more than one hidden layer.
I am interested in how to make this code more idiomatic - ...
7
votes
2answers
985 views
Python neural network: arbitrary number of hidden nodes
I'm trying to write a neural network that only requires the user to specify the dimensionality of the network. Concretely, the user might define a network like this:
...
5
votes
1answer
6k views
Simple Neural Network in Java
I had an assignment some weeks ago that consisted of making a simple McCulloch-Pitts neural network. I ended up coding it in a pretty OO style (or the OO style I've been taught), and I felt that my ...
2
votes
0answers
130 views
Back-propagation implementation
I've written an implementation of the back-propagation algorithm in Clojure (here). This is my first attempt at Clojure where the code totals more than ten lines and so it is not very idiomatic; ...
4
votes
1answer
2k views
Academic implementation of artificial neural network
With some free time, I decided to study artificial neural networks as an academic exercise (not homework). Over the course of my studies, I decided to write a Python application that would allow me to ...
3
votes
1answer
1k views
Basic neural network
I just programmed a basic neural network in F# to learn the logical OR function. As I am very new to F# and especially functional programming, I did it the imperative way. And even tho it works, I ...
4
votes
1answer
398 views
Back propagation neural network
This is the first time I tried to write a back propagation ANN and I would like to know what more experienced people think of it. The code is meant to distinguish if text is written in English, French ...
