Questions tagged [vanishing-gradient-problem]

For questions related to the vanishing gradient problem, which is a numerical problem that occurs while training a (deep) neural network with a gradient-based optimization technique. There's also the related exploding gradient problem.

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

Why aren't artificial derivatives used more often to solve the vanishing gradient problem?

While looking into the vanishing gradient problem, I came across a paper (https://ieeexplore.ieee.org/abstract/document/9336631) that used artificial derivatives in lieu of the real derivatives. For a ...
0 votes
0 answers
54 views

Why is the vanishing gradient problem more discussed than the exploding gradient problem in the context of deep CNNs?

Both vanishing and exploding gradient problems may occur if we increase the number of layers in CNN. It is due to the product operation in the chain rule. Whenever I read recent research papers, i.e. ...
  • 3,381
1 vote
1 answer
107 views

Mathematically speaking, Is it only the product operation used in the chain rule causing the vanishing or exploding gradient?

I am asking this question from the mathematical perspective of the vanishing and exploding gradient problems that we face generally during training deep neural networks. The chain rule of ...
  • 3,381
0 votes
0 answers
34 views

Is there any geometrical interpretation on overcoming gradient related problems by adjusting/changing loss function?

There are instances in literature where we need to change loss function in order to escape from gradient problems. Let $L_f$ be a loss function for a model I need to train on. Some times $L_f$ leads ...
  • 3,381
4 votes
0 answers
108 views

Why does sigmoid saturation prevent signal flow through the neuron?

As per these slides on page 35: Sigmoids saturate and kill gradients. when the neuron's activation saturates at either tail of 0 or 1, the gradient at these regions is almost zero. the gradient and ...
  • 183
1 vote
0 answers
96 views

How do I infer exploding or vanishing gradients in Keras?

It may already be obvious that I am just a practitioner and just a beginner to Deep Learning. I am still figuring out lots of "WHY"s and "HOW"s of DL. So, for example, if I train a ...
2 votes
1 answer
121 views

How does vanish gradient restrict RNN to not work for long range dependencies?

I am really trying to understand deep learning models like RNN, LSTMs etc. I have gone through many tutorials of RNN and have learned that RNN cannot work for long Range dependencies, like: Consider ...
2 votes
0 answers
169 views

How to decide if gradients are vanishing?

I am trying to debug a convolutional neural network. I am seeing gradients close to zero. How can I decide whether these gradients are vanishing or not? Is there some threshold to decide on vanishing ...
  • 121
0 votes
0 answers
55 views

In LSTMs, how does the additive property enables better balancing of gradient values during backpropagation?

There are two sources that I'm using to to try and understand why LSTMs reduce the likelihood of the vanishing gradient problem associated with RNNs. Both of these sources mention the reason LSTMs are ...
3 votes
0 answers
69 views

Would a different learning rate for every neuron and layer mitigate or solve the vanishing gradient problem?

I'm interested in using the sigmoid (or tanh) activation function instead of RELU. I'm aware of RELU advantages on faster computation and no vanishing gradient problem. But about vanishing gradient, ...
5 votes
2 answers
131 views

What are the common pitfalls that we could face when training neural networks?

Apart from the vanishing or exploding gradient problems, what are other problems or pitfalls that we could face when training neural networks?
  • 51
1 vote
1 answer
67 views

Does the paper "On the difficulty of training Recurrent Neural Networks" (2013) assume, falsely, that spectral radii are $\ge$ square matrix norms?

(link to paper in arxiv) In section 2.1 the authors define $\gamma$ as the maximum possible value of the derivative of the activation function (e.g. 1 for tanh.) Then they have this to say: We ...
2 votes
1 answer
145 views

How do LSTM and GRU avoid to overcome the vanishing gradient problem?

I'm watching the video Recurrent Neural Networks (RNN) | RNN LSTM | Deep Learning Tutorial | Tensorflow Tutorial | Edureka where the author says that the LSTM and GRU architecture help to reduce the ...
  • 1,343
5 votes
1 answer
651 views

What effect does batch norm have on the gradient?

Batch norm is a technique where they essentially standardize the activations at each layer, before passing it on to the next layer. Naturally, this will affect the gradient through the network. I have ...
5 votes
1 answer
588 views

If vanishing gradients are NOT the problem that ResNets solve, then what is the explanation behind ResNet success?

I often see blog posts or questions on here starting with the premise that ResNets solve the vanishing gradient problem. The original 2015 paper contains the following passage in section 4.1: We ...
1 vote
0 answers
254 views

Which activation functions can lead to the vanishing gradient problem?

From this video tutorial Vanishing Gradient Tutorial, the sigmoid function and the hyperbolic tangent can produce the vanishing gradient problem. What other activation functions can lead to the ...
  • 1,343
4 votes
1 answer
2k views

How to detect vanishing gradients?

Can vanishing gradients be detected by the change in distribution (or lack thereof) of my convolution's kernel weights throughout the training epochs? And if so how? For example, if only 25% of my ...
6 votes
1 answer
7k views

Why do ResNets avoid the vanishing gradient problem?

I read that, if we use the sigmoid or hyperbolic tangent activation functions in deep neural networks, we can have some problems with the vanishing of the gradient, and this is visible by the shapes ...
  • 179