All Questions
28 questions
1
vote
0
answers
35
views
Neural Network backpropagation algorithm only partially training in python
I am writing a neural network to identify digits from the MNIST database. It's primarily based on this code https://github.com/SebLague/Neural-Network-Experiments
My neural network appears to be ...
- 11
0
votes
1
answer
281
views
Why does my MLP model's loss explode when using softmax and cross entropy in Python?
I am writing an NLP model from scratch in Python, using only NumPy for most of the functions.
import numpy as np
# my loss and activation functions
def relu(x):
return np.maximum(0, x)
def ...
- 28
0
votes
0
answers
69
views
How to correctly backpropagate in a fully connected Neural Network?
I'm trying to write a neural network from scratch and It seems that I have misunderstood something or done something wrong because my model is not performing as well as it should. Can someone help me ...
- 196
0
votes
1
answer
69
views
Python-coded neural network does not learn properly
My network is not trained to recognize inputs separately, it either outputs the averaged result or becomes biased to one particular output. What am I doing wrong?
import numpy as np
sigmoid = lambda ...
- 2,011
2
votes
2
answers
515
views
Calculating gradient of NN in pure python
import numpy
# Data and parameters
X = numpy.array([[-1.086, 0.997, 0.283, -1.506]])
T = numpy.array([[-0.579]])
W1 = numpy.array([[-0.339, -0.047, 0.746, -0.319, -0.222, -0.217],
...
- 287
-2
votes
1
answer
32
views
where is the mistake in this neural network implementation?
I recently started to learn deep learning and I tried to write a forward and backward propagation from the beginning but I think there is a problem with my code so I know this is hard to find the ...
1
vote
1
answer
73
views
Backpropagation bug
I am trying to implement backpropagation from scratch. While my cost is decreasing, gradient check yields a whooping 0.767399376130221. I've been trying to figure out what's wrong and managed to slim ...
- 95
2
votes
1
answer
405
views
How to perform back propagation with different sized layers?
I'm developing my first neural network, using the well known MNIST database of handwritten digit. I want the NN to be able to classify a number from 0 to 9 given an image.
My neural network consists ...
- 1,144
0
votes
1
answer
67
views
Numpy Backprop Cost is Not Decreasing
I'm working on a python script that allows the user to define the number of hidden layers and their number of nodes in fully connected neural network.
The problem is, the error is coming up as nan ...
- 47
4
votes
1
answer
4k
views
How to correctly calculate gradients in neural network with numpy
I am trying to build a simple neural network class from scratch using numpy, and test it using the XOR problem. But the backpropagation function (backprop) does not seem to be working correctly.
In ...
- 41
0
votes
1
answer
422
views
Weights in Numpy Neural Net Not Updating, Error is Static
I'm trying to build a neural network on the Mnist dataset for a HW assignment. I'm not asking anyone to DO the assignment for me, I'm just having trouble figuring out why the Training accuracy and ...
- 47
0
votes
0
answers
296
views
Error regarding shapes not aligned back propagation
I am a newbie to machine learning and currently learning through Michael Nielsen's website... I am currently running code for handwritten digit recognition... The code is perfectly the same as given ...
-3
votes
2
answers
1k
views
How to calculate gradient descent cost for the weights using a dot product? [closed]
I'm trying to reproduce a neural network from http://neuralnetworksanddeeplearning.com/chap2.html
What i don't get is why they can calculate the gradient descent for the weights by taking a dot ...
- 30
1
vote
0
answers
169
views
neural network predicting same output class for every input while training also
I'm implementing a neural network using backpropogation algorithm in python.the method used is similar to that taught by Andrew Ng in his Machine Learning course.
But the NN is predicting same class ...
1
vote
1
answer
326
views
How to Input my Training Data into this Neural Network
I'm trying to solve a classification problem with a specific piece of code, and I'm having trouble understanding exactly how my data is to be fed into the Neural Network.
I started encoding the data ...
- 461