We’re rewarding the question askers & reputations are being recalculated! Read more.

Questions tagged [backpropagation]

For questions related to the technique of backpropagation, whereby the loss, error, or correction signal calculated at the output of an artificial network output is fed back to the parameters in each layer of the network until the network's behavior converges to a training state within the required accuracy and reliability.

Filter by
Sorted by
Tagged with
3
votes
1answer
42 views

What kind of data structures are needed to efficiently do back-propagation in a feedforward neural network?

In a feed-forward neural network, in order to efficiently do backpropagation, what kind of data structure is needed? I know the weights can just be stored in an array, and you need pointers of some ...
1
vote
0answers
31 views

How is gradient being calculated in Andrej Karpathy's pong code?

I was going through the code by Andrej Karpathy on reinforcement learning using a policy gradient. I have some questions from the code. Where is the logarithm of the probability being calculated? ...
3
votes
2answers
47 views

Which linear algebra book should I read to understand vectorized operations?

I am reading the Goodfellow's book about neural networks, but I am stuck in the mathematical calculus of the back-propagation algorithm. I understood the principle, and some Youtube videos explaining ...
1
vote
0answers
30 views

Understanding the partial derivative with respect to the weight matrix and bias

Say we have the layer $X W + b = Y$. I want to get $\frac{dL}{dW}$ and we assume I have $\frac{dL}{dY}$. So all I need is to find $\frac{dY}{dW}$. I know that it should be $X^T\frac{dL}{dY}$ but don'...
0
votes
1answer
45 views

Why is my neural network giving me wildly incorrect error and not changing accuracy?

My full code is as follows. I have tried to whittle it down to just the code that matters, but the problem I have is that i'm not sure what part of my network code is producing the problem. I've ...
2
votes
1answer
48 views

When and how to use a mix of loss functions for back-propagation?

I am trying to understand the best loss function to be used with a convolutional neural network. I came to know that we can mix two loss functions. Can any body share in what case was it done and how?
4
votes
2answers
32 views

Is the gradient at a layer independent of the activations of the previous layers?

Is the gradient at a layer (of a feed-forward neural network) independent of the activations of the previous layers? I read this in a paper titled Mean Field Residual Networks: On the Edge of Chaos (...
0
votes
1answer
50 views

Confused with backprop in pytorch with BCE loss

I've a prediction matrix(P) of dimension 3x3 and one-hot encoded label matrix(L) of dimension 3x3 as shown below. ...
2
votes
0answers
18 views

How does a Bidirectional RNN work?

Could it be possible to reach a similar output via feeding a unidirectional network with the original data and the data played backwards?
0
votes
1answer
26 views

Backpropagation: Chain Rule to the Third Last Layer

I'm trying to solve dLoss/dW1. The network is as in picture below with identity activation at all neurons: Solving dLoss/dW7 is simple as there's only 1 way to output: $Delta = Out-Y$ $Loss = abs(...
6
votes
2answers
59 views

Why do very deep non resnet architectures perform worse compared to shallower ones for the same iteration? Shouldn't they just train slower?

My understanding of the vanishing gradient problem in deep networks is that as backprop progresses through the layers the gradients become small, and thus training progresses slower. I'm having a hard ...
0
votes
1answer
67 views

How can the derivative of a neural network be calculated, given no mathematical expression?

Neural networks (NNs) are used as approximators in reinforcement learning (RL). To update the policy in RL, the actor network's gradients w.r.t its weights are needed. Since NN doesn't have a ...
3
votes
1answer
24 views

Structure discrepancy of an LSTM?

I've found multiple depictions of how an LSTM cell operates. See 2 below: and Each of these images suggest the hidden state is utilised differently. On the top diagram, it is shown that the hidden ...
1
vote
0answers
28 views

How does a single neuron in hidden layer affect training accuracy

I'm currently a student learning about AI Networks. I've came across a statement in one of my Professor's books that a FFBP (Feed-Forward Back-Propagation) Neural Network with a single hidden layer ...
1
vote
0answers
49 views

How to train and update weights of filters

I have some problems with training CNN :( For example: Input 6x6x3, 1 core 3x3x3, output = 4x4x1 => pool: 2x2x1 By backpropagation I calculated deltas for output. This tutor and other tutors are ...
3
votes
1answer
58 views

How is REINFORCE used instead of Backpropagation?

In neural networks with stochastic layers I've seen the use of the REINFORCE estimator for estimating the gradient (because it can't be computed directly). Some such examples are Show, Attend and ...
0
votes
0answers
33 views

Not able to properly tune Neural Network via Back Propagation properly

I have a custom code Neural Network(not using keras or any package...Trying to learn the essence of Neural Network from scratch)... Code can be found here I have the per iteration training output(<...
4
votes
1answer
75 views

Backpropagation equation for a variant on the usual Linear Neuron architecture

Recently I encountered a variant on the normal linear neural layer architecture: Instead of $Z = XW + B$, we now have $Z = (X-A)W + B$. So we have a 'pre-bias' $A$ that affects the activation of the ...
3
votes
1answer
46 views

What weights should I use while back-propagating?

I've started to learn about neural networks recently and I can't find the answer to this question. Let's assume there's a neural network (fig. 1) So if the loss function is: and the derivative is: ...
4
votes
1answer
46 views

How can I use one neural network for both players in Alpha Zero (Connect 4)?

First of all, it is great to have found this community! I am currently implementing my own Alpha Zero clone on Connect4. However, I have a mental barrier I cannot overcome. How can I use one neural ...
2
votes
1answer
36 views

How is a neural network where the majority of inputs are 0 trained?

Take alexnet. Alexnet has 1000 output nodes, each of which classify an image: The problem I have been having with training a neural network of similar proportions, is that it does what any reasonable ...
0
votes
0answers
35 views

Confused about NeuralODE

I am a bit confused about NeuralODE and I want to make sure that what I understood so far is correct. Assume we have (for simplicity) 2 data points $z_0$ measured at $t_0$ and $z_1$ measured at $t_1$...
0
votes
1answer
47 views

Back propagation on matrix of weights

I am trying to implement a Neural Network for binary classification using python and numpy only. My network structure is as follows: input features: 2 [1X2] matrix Hidden layer1: 5 neurons [2X5] ...
0
votes
0answers
51 views

Updating biasses while backpropagation in all details

I just wabt to ask do i understand the usage and updating biasses while backpropagating and what values comes where. Let us see following network : with bach size 6, input size 2, hidden size 4 and ...
3
votes
3answers
75 views

How does adding a small change to an neuron's weighted input affect the overall cost?

I was reading the following book: http://neuralnetworksanddeeplearning.com/chap2.html and towards the end of equation 29, there is a paragraph that explains this: However I am unsure how the ...
1
vote
1answer
109 views

Do you need to store prevous values of weights and layers on recurrent layer while BPTT?

The Back propagation through time on recurrent layer is defined similar to normal one, means somethin like ...
4
votes
1answer
118 views

How are filters weights updated for a CNN?

I've been trying to learn backpropagation for CNNs. I read several articles like this one and this one. They all say that to compute the gradients for the filters, you just do a convolution with the ...
1
vote
0answers
47 views

Difficulties to implement the layer-wise relevance propagation in MATLAB

I'm having serious issues with the implementation of the LRP algorithm for neural networks in MATLAB. The challenge is to implement the equations correctly. I'm trying to implement the deep-Taylor $\...
0
votes
2answers
103 views

How should the values of the filters of a CNN change?

I wrote a convolutional neural network for the MNIST dataset with Numpy from scratch. I am currently trying to understand every part and calculation. But one thing I noticed was the "just positive" ...
1
vote
0answers
41 views

How are the weights between the input and hidden layer updated in a 3 layer neural network?

Consider a feed-forward neural network with one hidden layer. How are the weights between the input and hidden layer updated, after the weights between the hidden layer and output layer are updated?
1
vote
1answer
57 views

When is bias values updated in back propagation?

I am new to deep learning. I have doubts on modifying bias values during back propagation. My doubts are Does the back propagation algorithm modifies the weigh values and bias values in the same pass?...
1
vote
1answer
117 views

Is back propagation applied for each data point or for a batch of data points?

I am new to deep learning and trying to understand the concept of back propagation. I have a doubt on when the back propagation is applied. Assume that I have a training data set of 1000 images for ...
0
votes
1answer
181 views

Back propagation on Flatten Layer in CNN

I am making a NN library without any other external NN lib and is implementing the Flatten layer. I know the forward implementation of flatten layer but is the backward just reshaping it or not? If ...
5
votes
2answers
103 views

Are on-line backpropagation iterations perpendicular to the constraint?

Raul Rojas' Neural Networks A Systematic Introduction, section 8.1.2 relates off-line backpropagation and on-line backpropagation with Gauss-Jacobi and Gauss-Seidel methods for finding the ...
2
votes
1answer
97 views

What is the difference between backpropagation and predictive coding?

Reading the high-level descriptions of backpropagation and predictive coding, they don't sound so drastically different. What is the key difference between these techniques? I am currently reading ...
0
votes
0answers
105 views

How to back-propagate illegal actions for policy gradient learning

When training a AI RL agent to play a game there'll be situations where the AI cannot perform certain actions lest they violate the game rules. That's easy to handle, and I can set illegal actions to ...
1
vote
1answer
39 views

Which local minima to choose according to the shape of the error surface?

The following plot shows error function output based on system weights. Two equal local minima are shown in green pointers. Note that the red dots are not related to the question. Considering the ...
3
votes
2answers
60 views

Could error surface shape be useful to detect which local minima is better for generalization?

The following plot shows error function output based on system weights. Two equal local minima are shown in green pointers. Note that the red dots are not related to the question. Does the right one ...
1
vote
1answer
110 views

How does backpropagation with unbounded activation functions such as ReLU work?

I am in the process of writing my own basic machine learning library in Python as an exercise to gain a good conceptual understanding. I have successfully implemented backpropagation for activation ...
1
vote
1answer
148 views

A neural network for digits recognition doesn't work (MNIST, Numpy) [closed]

I'm a beginner in machine learning and I was trying to make a test neural network for digits recognition from scratch using Numpy. I used MNIST dataset for training and testing. Input layer have 28*28 ...
2
votes
2answers
76 views

Which neuron represents which part of the input?

In a neural network, each neuron represents some part of the input. For example, in the case of a MNIST digit, consider the stem of the number 9. Each neuron in the NN represents some part of this ...
0
votes
1answer
66 views

Training the generator in a GAN pair with back propagation

For the purposes of this question I am asking about training the generator, assume that training the discriminator is another topic. My understanding of generative adversarial networks is that you ...
0
votes
1answer
271 views

Feed forward neural network using numpy for IRIS dataset

I tried to build a neural network for working on IRIS dataset using only numpy after reading an article (link: https://iamtrask.github.io/2015/07/12/basic-python-network/). I tried to search the ...
1
vote
2answers
245 views

What is the derivative function used in backpropagration?

I'm learning AI, but this confuses me. The derivative function used in backpropagation is the derivative of activation function or the derivative of loss function? These terms are confusing: ...
2
votes
1answer
45 views

What is the use of the $\epsilon$ term in this back-propagation equation?

I am currently looking at different documents to understand back-propagation, mainly at this document. Now, at page 3, there is the $\epsilon$ symbol involved: While I understand the main part of the ...
4
votes
1answer
40 views

Am I able to visualize the differentiation in backprop as follows?

I'm wondering if I can visualize the backprop process as follows (please excuse me if I have written something terrible wrong). If the loss function $L$ on a neural network represents the function has ...
1
vote
1answer
24 views

Training by one batch of examples, what does it mean

Say I have a batch of examples, each examples represent a state: ...
4
votes
4answers
397 views

What is the actual learning algorithm: back-propagation or gradient descent?

What is the actual learning algorithm: back-propagation or gradient descent (or, in general, the optimization algorithm)? I am reading through chapter 8 of Parallel Distributed Processing hand book ...
1
vote
0answers
28 views

Use of backpropagation for weight updates in a combination of 2 neural networks

Every neural network updates its weights through back-propagation. How is back-propagation used for updating weights in a combination of 2 or more neural networks (e.g.:CNN-LSTM, GAN-CNN, etc.). For ...
2
votes
0answers
96 views

Update of weights in Recurrent Neural Network through back propagation

How does Recurrent Neural Network updates its weights and bias through backpropagation? Is time taken into account while updating the weights of a RNN using Backpropagation through time(BPTT)?"