Questions tagged [neural-network]
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.
117
questions
1
vote
0
answers
48
views
Convolutional Neural Network (CNN) in Julia
I wrote an n-dimensional convolutional neural network from scratch in Julia (check out the GitLab repo or the GitHub repo). It implements the following layer types:
...
0
votes
0
answers
30
views
Running a neural network backwards
I've read this paper where they basically run a network backwards.
And decided to try. Luckily, many useful functions are implemented already in pytorch.
The main idea is this:
Write a convnet
Write ...
- 239
1
vote
0
answers
42
views
Recurrent Neural Network loss is NAN
I am training a neural network to use approximately 600 features (4103rd to last column of a df) to predict approximately 4000 values (7th to 4102nd column of the same df). I have standardized the ...
- 11
6
votes
3
answers
533
views
Feed forward neural network
I have made a basic neural network in python. The idea is the neural network can have any structure you want, not just the standard layers where every neuron is connected to every neuron in the next ...
- 179
2
votes
1
answer
119
views
ANN with Backpropagation for MINST data set
I am learning about ANN and tried it for the MINST data sets. Now I am supposted to create a neural network (ANN) with backpropagation.
The structure for the neural network I have is this the input ...
- 47
1
vote
1
answer
68
views
Neural Network in Julia (Multilayer Perceptron)
I wrote a simple multilayer perceptron in Julia, which seems to work fine on different datasets, e.g. the MNIST dataset with a success rate of about 90% after a few seconds of training. But I would ...
1
vote
1
answer
56
views
Optimize an algorithm for preparing a dataset for machine learning
I'm learning how to use R coming from a python background. I'm following Andrej Karpathy's zero-to-hero course, reimplementing it in R.
We start with a list of 32033 names. These names have to be ...
- 35
1
vote
1
answer
47
views
Readable Backprogragation calculations in Numpy Neural Network
As an exercise we should write a small Neural Network with the following structure:
There should be additionally a bias for each layer and sigmoid should be used as the activation function.
The ...
- 41
0
votes
0
answers
22
views
custom IoU loss for object detection training in Tensorflow2
I am training a single-class object detection model in Tensorflow/Keras. The input image can contain either 0 or 1 instances of the object of interest (no multiple bounding boxes). My model outputs ...
- 111
2
votes
0
answers
77
views
neural network that determines the gender of a word
I wrote a neural network in python using pytorch, which determines the gender of a word in Russian. As a training set: a file containing a word and a number from 0 to 2 (0-masculine,1- feminine and 2-...
- 21
1
vote
0
answers
116
views
Binary classification with pytorch
I wrote a simple neural network binary classification algorithm using Pytorch. It uses the dataset from https://www.kaggle.com/pritsheta/heart-attack, which consists of a table with 300 rows and 14 ...
- 163
4
votes
1
answer
76
views
Unsupervised competitive learning algorithm from scratch in javascript
I'm a mathematician who is new to programming and I'm currently reading the book "Theory of Neural Networks" by Rojas. To become better, I try to program every algorithm that is described in ...
- 151
2
votes
0
answers
52
views
DQN implementation
I just wrote my pong DQN. It seems to work. I'm looking for a performance based review on anything that might slow down the training in complex models.
main.py:
...
2
votes
2
answers
80
views
Updated version of my first neural network in c++
I got lot of suggestions for optimizing my neural network last post I made, now I wanted to post updated version of it were I got rid of most of performance eaters, now I would really appriciate ...
- 31
8
votes
3
answers
727
views
My first functional naive neural network in C++
I just wrote my first standard neural network with SGD gradient descent in c++, I am really interested if I have done anything wrong or inefficient, suggestions would help me a ton
(There is lots of ...
2
votes
1
answer
93
views
Loss function in python is a bit cumbersome
Here is a python function I have for a neural network I have implemented. I feel it become a bit cumbersome. The intention is to weight positive labels in channels ...
- 159
4
votes
1
answer
98
views
Working Neural Net from scratch
Asking for a review of this neural network code.
I have officially finished my first neural net that works properly (by my standards right now). But I know there is more than likely some details I am ...
- 55
4
votes
1
answer
128
views
Neural Network Written in Python is Extremely Slow
I coded a basic feedforward neural network with all pure python with the exception of numpy in order to better understand how neural networks work. It works, but the only problem is it is extremely ...
- 41
1
vote
1
answer
133
views
Neural net backprop code quality
This is my first neural net, previously I had it with just one hidden layer.
I have now given it an adjustable number of hidden layers. It all works perfectly (asin I dont get nans and infs). I have ...
- 55
1
vote
1
answer
75
views
Does this feedforward neural network work like i think it works?
I seem to have taught myself the basics of c++ living off grig in the woods of Alaska.
Most of this has been done on my android phone using cpp droid.
This is the first time anyone has seen any of my ...
- 127
4
votes
0
answers
96
views
Using VAE for reconstructing images
Article: https://arxiv.org/pdf/2009.07047v1.pdf
Full Code: https://colab.research.google.com/drive/1KZZuIa7Lk13ImZLJ3b-kxMfcveOPaWvN#scrollTo=XhdMfBFtzaEH
Dataset: https://drive.google.com/file/d/...
- 41
2
votes
0
answers
47
views
Generator and Encoder network model [closed]
https://arxiv.org/pdf/2009.07047v1.pdf
I don't have a lot of experience in building a network model. I would like to build the Encoder and ...
- 121
1
vote
0
answers
77
views
Implementing Convolutional Neural Network
Context
I was making a Convolutional Neural Network from scratch in Python. I completed making it .... It works fine ... The only thing is that it takes a lot of time as the size of the input grows.
...
- 193
7
votes
1
answer
114
views
A .py utility file for neural network learing rate policies
I've created a .py utility file, which specifies the learning rate policy for the neural network in PyTorch. The program in prior reads a ...
3
votes
0
answers
76
views
Constraining monotonicity in the loss function during training
I have a neural network that I am training on a loss function composed of two terms (i.e. loss = loss1 + loss2). Ideally, I would like for both ...
- 131
4
votes
1
answer
63
views
Python implementation of Back Propagation Algorithm without bias
This program implements the back propagation algorithm of neural network with an example. Can we make it more efficient?
...
- 223
6
votes
1
answer
942
views
Simple neural network in c++
I have implemented a neural network in C++. But I'm not sure whether my implementation is correct or not. My code of the implementation of neural networks given bellow.
As an inexperienced programmer, ...
- 63
6
votes
1
answer
220
views
Using Newton Method in a Neural Network/
I programmed a Neural Network to do binary classification in python, and during the backpropagation step I used Newton-Raphson's method for optimization. Any kind of feedback would be appreciated, but ...
- 61
1
vote
1
answer
112
views
LSTM Model - Validation Accuracy is not changing
I am working on classification problem, My input data is labels and output expected data is labels
Labels Count
1 94481
0 65181
2 60448
I have made ...
- 27
1
vote
0
answers
245
views
Lazy loading generator for training a Keras network
A common use for Keras LSTM layers is to generate text. There are
many examples showing you how to do it.
The usual method is to convert the text into a sequence of tokens and
then slice up the ...
- 1,342
3
votes
1
answer
730
views
MNIST Neural network in C++
While reading an online book (Michael A. Nielsen, Neural Networks and Deep Learning, Determination Press, 2015) regarding neural networks, I decided I wanted to try and build a neural network which ...
- 33
2
votes
0
answers
50
views
simple neural network in python
I've spent the last few days learning the beginnings of how to implement a simple neural network. I've gone through chapters 1 and 2 of this book and have tried to write my own NN with referrals to ...
- 61
1
vote
0
answers
52
views
A function for batch backpropagation of weight errors in a dense neural network layer
I'm switching my neural network library over to using ArrayFire for performance.
One of the features I am losing moving from ndarray is ndarray_einsum_beta, as such I need to write my own function to ...
3
votes
1
answer
36
views
Creating generator object with image augmentation to train Convolutional Neural Networks with Keras
I am currently self-studying on Python generator object and use it to generate training data and do augmentation on-the-fly, then feed it into Convolutional Neural Networks.
Could anyone please help ...
- 131
2
votes
0
answers
105
views
Multi-threaded HD Image classifier using a neural network
This is a follow up to the code found here:
Multithreaded HD Image Processing + Logistic reg. Classifier + Visualization
Description:
This code takes a label and a folder path of subfolders as ...
6
votes
2
answers
208
views
A Neural Network
I programmed a Neural Network in python. Feedback every kind is appreciated.
I tried to use some vectorization but it turned out to become quite a mess. Because you can't append to numpy arrays I ...
- 163
2
votes
1
answer
89
views
Java Neural Network Implementation
I have recently tried to get a better grip on machine learning from a point of implementation - not statistics. I've read several explanations of an implementation of a Neural Network via pseudocode ...
1
vote
0
answers
98
views
Neural network from scratch in Python
So after watching week 5 of the machine learning course on Coursera by Andrew Ng, I decided to write a simple neural net from scratch using Python. Here's my code:
...
user209945
-1
votes
1
answer
125
views
Python ANN Implementation [closed]
I recently learned about backpropagation online and tried to implement it. I am not sure I have it correct yet. I am confused and would love a second pair of eyes on this code. Please help me ...
9
votes
1
answer
330
views
Neural Network with Template Metaprogramming
I was implementing a simple neural network, and I noticed that, if I ever wanted to change the layers' activation functions, i would have had to completely rewrite some parts of the code, so I tried ...
- 633
6
votes
1
answer
80
views
Implementation of perceptron, inspired by Rashka
I am trying to learn the basics about neural networks by coding from scratch the perceptron model.
Since I am not a programmer and would like to improve my coding skills I would like to get your ...
- 103
8
votes
1
answer
245
views
Deep Neural Net implementation in Python3
I created my first implementation of an arbitrary feed forward neural network with a simple back-propagation training implementation.
...
- 205
3
votes
0
answers
1k
views
A simple toy ResNet model and its implementation
I want to understand how resnet works also called us residual networks and I understand it better when I code one myself. I tried to find a simple implementation of resnet in the web but most I found ...
- 349
1
vote
0
answers
299
views
Custom Vector and Matrix classes in python for machine learning
I am creating a machine learning tool set from scratch in python. I have never done something of this kind and I don't usually use python but I thought it would be good to expand my horizons. I am ...
- 111
4
votes
1
answer
767
views
Artificial Neural Network Classifier in Matlab
I am trying to build a neural network classifier. I have created a neural network with 1 hidden layer (25 neurons) and 1 output layer (1 neuron/binary classification).
The dataset I am using has the ...
- 193
2
votes
0
answers
196
views
Simple Neural Network from scratch using NumPy (Python)
I added learning rate and momentum to a neural network implementation from scratch I found at: https://towardsdatascience.com/how-to-build-your-own-neural-network-from-scratch-in-python-68998a08e4f6
...
- 43
2
votes
1
answer
61
views
Haskell 'n' layered ANN forward pass
I'm trying to write a simple 'n' layered ANN in haskell for supervised learning, it will eventually have back prop and you'll be able to use it in a step by step fashion through a GUI which will graph ...
- 200
6
votes
1
answer
115
views
Simple neural network implementation in Python
A simple neural network I wrote in Python without libraries. I avoided implementing it in matrix form because I sought to get a basic understanding of the way NN's work first. For that reason I'm ...
- 121
3
votes
2
answers
219
views
How to make my neural network train faster
I'm trying to train my neural network and for the most part it's going well. However, I'd like it if it could train faster and was wondering if anyone could give some advice.
I'm trying mostly to ...
- 35
2
votes
0
answers
158
views
Neural Network Backpropagation
My neural network is buggy somewhere. However, the reason I am posting here and not Stack Overflow is because a buggy neural network can still be trained to some degree and will compile/perform better ...
- 927