Questions tagged [weights]
For questions about the concept of weight (or parameter) of a machine learning model, such as a neural network or a linear regression model.
75
questions
0
votes
0answers
4 views
Are there any recommendations on initialising a single parameter in deep learning?
I want to initialize a parameter, which is a single real number in my model. If you want the role of the parameter in the model, you can assume it as the parameter to multiply with the output of the ...
0
votes
0answers
15 views
Custom layers in Keras -- defining weights [closed]
I am trying to understand how to build custom layers in Keras and I went through a couple examples: here and here. The syntax is, of course, similar, but in non of the cases it is addressed why ...
3
votes
0answers
41 views
Are there neural networks with (hard) constraints on the weights?
I don't know too much about Deep Learning, so my question might be silly. However, I was wondering whether there are NN architectures with some hard constraints on the weights of some layers. For ...
0
votes
0answers
17 views
Rank of gradient-of-loss with respect to layer weights in an MLP
The paper: https://arxiv.org/abs/2110.11309, makes the following claim at the end of page 3:
The gradient of loss $L$ with respect to weights $W_l$ of an MLP is a rank-1 matrix for each of B batch ...
2
votes
0answers
22 views
Derivation of weights for linear function approximation of Temporal difference method
https://web.stanford.edu/class/cs234/slides/lecture5.pdf
I am reading the above material. On page 38, the update for the parameters for the linear function approximation of TD(0) is given. I have a ...
-2
votes
1answer
30 views
model and trained model parameters on CIFAR-10 [closed]
I'm looking for different models (specifically ResNet18/20, ResNet32/34, VGG16, MobileNet and SqueezeNet) and their parameters after training (i.e., .pth file) that ...
1
vote
1answer
38 views
Is there a way to update the neural network to fit the new data without the time required for retraining?
I built a basic neural network in MATLAB. The neural network classifies points on the X-Y axis system into two classes (0 and 1).
(I try to get the function that represents a shape from this photo)
...
0
votes
0answers
48 views
What would be the total number of learnable parameters of the RNN encoder of this encoder-decoder architecture for machine translation?
Here's a quiz. My answer is different from the teacher's, so I'm wondering what answer would you pick up.
We use a sequence-to-sequence (encoder-decoder) system to perform
machine translation. We ...
1
vote
0answers
23 views
In mini-batch gradient descent, are the weights updated after each batch or after all the batches have gone through an epoch?
Say I have a mini-batch of size 32, and I have 10 such batches. Assuming I only run it for one epoch (just for the sake of understanding it), Will the weights be updated using the gradients of one ...
0
votes
2answers
51 views
Correctly input additional values into CNN
I understand that in order to add additional inputs to a CNN, e.g. in self driving, I can append the data to a flattened layer after the convolutions and before the fully connected layers.
However, a ...
1
vote
0answers
34 views
Using parameter estimation for training a neural network
Assume that we have 4 layers in a neural network.
$$z_1 = L_1(x, W_1)$$
$$z_2 = L_2(z_1, W_2)$$
$$z_3 = L_3(z_2, W_3)$$
$$y = L_1(z_3, W_4)$$
Where $x$ is the vector input, $y$ is the vector output ...
0
votes
0answers
22 views
How did authors ensure that critical points do exist in GAN?
Using an MLP as a generator introduces multiple critical points in parameter space. You can read this excerpt from the research paper titled Generative Adversarial Nets by Ian J. Goodfellow et al.
In ...
1
vote
0answers
23 views
Is there a proper initialization technique for the weight matrices in multi-head attention?
Self-attention layers have 4 learnable tensors (in the vanilla formulation):
Query matrix $W_Q$
Key matrix $W_K$
Value matrix $W_V$
Output matrix $W_O$
Nice illustration from https://jalammar....
0
votes
0answers
7 views
Are there any connectionist parametric models with non-neuron building blocks?
Parametric models allows learning by converging to the desired parameters, which are randomly initialized initially. Among the parametric models, especially in connectionist AI, neural networks are ...
0
votes
0answers
23 views
How to handle critical points during generator training?
Using an MLP as a generator introduces multiple critical points in parameter space. You can read this excerpt from the research paper titled Generative Adversarial Nets by Ian J. Goodfellow et al.
In ...
1
vote
0answers
16 views
Recursive Least squares (RLS) for mini batch
For my application I am considering a learning problem where I simulate a bunch of episodes say '$n$' first, and than carry out the recursive least squares update. Similar to $TD(1)$.
I know that RLS ...
0
votes
1answer
43 views
Is precision of weights unimportant in neural networks?
While reading about Module in PyTorch, I came across a new data type called half datatype.
half() method when calls on a Module ...
0
votes
0answers
49 views
What are the numbers that are useful (may need to be stored) other than parameters of a model?
Consider the following method related to buffers in PyTorch
...
3
votes
1answer
58 views
Can some of the weights be fixed during the training of a neural network?
Is it possible to exclude specific layers from the optimization?
For example, let's say I have an input layer, 2 hidden layers, and the output layer. I know there is a perfect solution for my problem ...
0
votes
0answers
15 views
Prioritized Experience Replay, clarifications for Important Sampling
I can't seem to understand how the weight equation is dissected and how it really works when combined with the TD-error value. The weight equation is:
I can understand what N, P(i) and beta represent,...
1
vote
1answer
51 views
Which solutions are there to the problem of having too large activations before the softmax (or sigmoid) layer?
I'm trying to build a neural network (NN) for classification using only N-bit integers for both the activations and weights, then I will train it with some heuristic algorithm, based only on the NN ...
1
vote
0answers
296 views
If I have a feature matrix of shape $1200 \times 2000$, should I have $2000$ input neurons?
I have an input feature matrix (row-normalized) of size $1200 \times 2000$.
When I am writing my neural network, is the number of input neurons equal to the number of columns, that is $2000$?
Is it ...
2
votes
1answer
32 views
Why are weights not initialized with mean=1?
I wonder why weights are initialized with zero-mean. It is one of the reasons, why deep architectures cannot be trained without skip connections. Without the skip connections, the zero initialization ...
2
votes
0answers
21 views
Which methods for weight initialization in Neural Networks are currently common practice?
I am currently researching the topic of weight initialization methods for (deep) neural networks and I'm a little stuck. The result of my work should be an overview of methods that are currently in ...
4
votes
1answer
124 views
Is the bias also a "weight" in a neural network?
I'm learning about how neural networks are trained. I understand how a neuron works, backpropagation, and all that. In neurons, there is a clear distinction between a "weight" and a "...
1
vote
0answers
18 views
What is the effect and behavior of using mixed weight instead of normal weight matrix?
Suppose I try to find appropriate matrix A in differential equation $\dot{X}=A X$ using RNN.
Current state is $X=\begin{bmatrix}
x_{1}\\
x_{2}\\
\end{bmatrix}$, and desired trajectory state is $X_d=\...
1
vote
0answers
13 views
How to update all the weights in case only one data out of n signals is observable
If we have cost function as
$$E_i = (D_i -Y_i)^T Q (D_i -Y_i)$$,
where $$Q=\begin{bmatrix}
1 & 0 & 0\\
0 & 0 & 0\\
0 & 0 & 0
\end{bmatrix}$$( in case only one data signal can ...
2
votes
1answer
56 views
Is this LSTM layer learning anything?
I've trained a CNN-LSTM model but the results weren't satisfactory, so I took a look at my weight distributions and this is what I got:
I don't understand. Is this layer learning anything? Or no?
...
1
vote
1answer
40 views
How to train a neural network with few weights and biases held constant?
I am a beginner in neural networks. I am building a neural network with 3 layers. The input $X$ has 7 features and the output $Y$ is a real number. In the hidden layer, there are two nodes. The bottom ...
6
votes
1answer
149 views
Why did the developement of neural networks stop between 50s and 80s?
In a video lecture on the development of neural networks and the history of deep learning (you can start from minute 13), the lecturer (Yann LeCunn) said that the development of neural networks ...
2
votes
1answer
47 views
Does the weight vector form imply feature space curvature?
I came across this sentence when exploring a simple nearest neighbor classifier method using Euclidean distance (link):
The slightly odd thing about using the Euclidean distance to compare features ...
2
votes
1answer
109 views
Is there a convention on the order of multiplication of the weights with the inputs in neural nets?
Is there a convention on how the input data and the weights are multiplied? The input data can be anything, including the result from the previous layers.
There are two options:
Option 1:
$$\begin{...
5
votes
0answers
48 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 ...
2
votes
0answers
63 views
Are there any new weight initialization techniques for DNN published after 2015?
Considering weights initialization in my personal projects, I always used some standard techniques such as:
Glorot (also known as Xavier) initialization (2010).
Mertens initialization (2010).
He ...
1
vote
1answer
54 views
What are acting as weights in a convolution neural network?
Looking at some old notes I took on CNN's and I wrote down that the weights in a CNN are acting like filters in a CNN but to be honest I don't really know what the weights are acting as in a CNN and ...
0
votes
0answers
25 views
How do we interpret the images of weights in logistic regression
The following images are
a) The weights of a logistic regression model trained on MNIST.
b) The sign of the weights of a logistic regression
How do these images represent the weights?
Would be ...
0
votes
1answer
37 views
What does "adding class weights for an imbalanced dataset" mean in the case of multi-label classification?
Suppose I have the following toy data set:
Each instance has multiple labels at a time.
You can see I have 2 instances for Label2. However, only one instance for the other labels. It means that we ...
4
votes
0answers
46 views
When is using weight regularization bad?
Regularization of weights (e.g. L1 or L2) keeps them small and standardized, which can help reduce data overfitting. From this article, regularization sounds favorable in many cases, but is it always ...
1
vote
0answers
61 views
Is the performance of a neural network, which was trained with encrypted data and weights, affected if the weights are decrypted?
Suppose that a neural network is trained with encrypted (for example, with homomorphic encryption and, more precisely, with the Paillier partial scheme) data. Moreover, suppose that it is also trained ...
5
votes
0answers
68 views
Why is there a Uniform and Normal version of He / Xavier initialization in DL libraries?
Two of the most popular initialization schemes for neural network weights today are Xavier and He. Both methods propose random weight initialization with a variance dependent on the number of input ...
1
vote
1answer
94 views
In attention models with multiple layers, are weight matrices shared across layers?
In articles that describe neural architectures with multiple attention layers of the same form, are the weight matrices usually the same across the layers? Consider as an example, "Attention is ...
1
vote
2answers
141 views
In the multi-head attention mechanism of the transformer, why do we need both $W_i^Q$ and ${W_i^K}^T$?
In the Attention is all you need paper, on the 4th page, we have equation 1, which describes the self-attention mechanism of the transformer architecture
$$
\text { Attention }(Q, K, V)=\operatorname{...
2
votes
0answers
63 views
Why should variance(output) equal variance(input) in Xavier Initialisation?
In a lot of explanations online for Xavier Initialization, I see the following:
With each passing layer, we want the variance to remain the same. This helps us keep the signal from exploding to a ...
0
votes
0answers
78 views
How many parameters does the AI of a typical self driving car have?
I can find the number of parameters AIs such as GPT3 or OpenAI Five have, but I'm having a difficult time googling the number of parameters a self driving car has because Google searches keeps using ...
4
votes
0answers
48 views
How efficient is SCAWI weight initialization method?
I'm currently in the middle of a project (for my thesis) constructing a deep neural network. Since I'm still in the research part, I'm trying to find various ways and techniques to initialize weights. ...
2
votes
1answer
50 views
Should the range and initial values of weights and biases be adjusted to fit input and output data?
As a routine (in typical everyday tasks) of a data scientist, should they usually decide about weights and biases range and initial values as a function of which data they are planning to insert as ...
2
votes
1answer
98 views
Which hyperparameters in neural network are accesible to users adjustment
I am new to Neural Networks and my questions are still very basic.
I know that most of neural networks allow and even ask user to chose hyper-parameters like:
amount of hidden layers
amount of ...
5
votes
2answers
160 views
What is the goal of weight initialization in neural networks?
This is a simple question. I know the weights in a neural network can be initialized in many different ways like: random uniform distribution, normal distribution, and Xavier initialization. But what ...
1
vote
1answer
75 views
What are some examples of functions that machine learning models compute?
My simple understanding of AI is that it is based on a mathematical model of a problem. If I understood correctly, the model is a polynomial equation and its weights are calculated by training the ...
1
vote
1answer
39 views
Are there examples of agents that use a more modest number of parameters on Pendulum (or similar environments)?
I'm looking at some baseline implementations of RL agents on the Pendulum environment. My guess was to use a relatively small neural net (~100 parameters).
I'm comparing my solution with some ...
