All Questions

Filter by
Sorted by
Tagged with
1
vote
1answer
9 views

Parallelised my training or the dataset

I have some plans in working with Reinforcement Learning in order to predict the stock price movement. For a stock like TSLA, some training features might be the pivot price values and the set of the ...
-1
votes
0answers
7 views

Spinningup Vanilla Policy Gradient - Where Does it uses critic network

I got a bit into the documentation and git pages of VPG of Spinningup.LINK One big thing that bugs me - I can't find the place where the actor network uses the critic network evaluation in order to ...
1
vote
0answers
10 views

What is an “additional channel dimension” contain in batch normalization?

Consider the following explanations regarding a batch normalization layers in PyTorch #1: one dimensional batch normalization class torch.nn.BatchNorm1d(.........) Applies Batch Normalization over a ...
1
vote
0answers
15 views

Reinforcement learning algorithms that deal with noisy state observations

I was recently considering training an agent that perform a task by reinforcement learning. Both the state and actions are continuous, but could be discretized if needed. The problem is that in my ...
0
votes
1answer
24 views

Why is it called “batch” gradient descent if it consumes the full dataset before calculating the gradient?

While training a neural network, we can follow three methods: batch gradient descent, mini-batch gradient descent and stochastic gradient descent. For this question, assume that your dataset has $n$ ...
1
vote
0answers
20 views

What does it mean there is no rollout in AlphaZero's training?

According to a blog post by DeepMind, AlphaZero doesn't have a real rollout. AlphaGo Zero does not use "rollouts" - fast, random games used by other Go programs to predict which player will ...
0
votes
0answers
25 views

How to measure the significance of an input feature for the output of a linear layer in a neural network

Suppose I have a simple linear layer $y = xA^T + b$ that is part of a neural network trained on some dataset. The weight matrix $A$ for this layer has the shape ...
0
votes
0answers
11 views

Multi label segmentation in pytorch/keras

I am currently working on a project related to Multi label segmentation. I haven't been able to find any substantial papers where objects in images were segmented based on a membership function. For ...
0
votes
0answers
22 views

At what point are MCTS results discarded in AlphaZeros Training?

Regarding the AlphaZero paper, it is not clear to me when the Monte Carlo Tree Search (MCTS) results will be cleaned up. I assume this has to happen at some point, since mixing results could lead to ...
1
vote
1answer
12 views

Cover a surface with smaller predefined objects

I'm trying to make a program that takes a surface designed by the user, and different 3D geometries from a dataset as inputs and gives a good approximation of the surface using only the objects found ...
0
votes
1answer
22 views

Is a convolutional layer capable of converting, for example, a binary image into, for example, an RGBA image?

I am asking this question for a better understanding of the concept of channels in images. I am aware that a convolutional layer generates feature maps from a given image. We can adjust the size of ...
1
vote
0answers
17 views

Training on the dataset in parts vs training on the whole dataset

What is the difference between these two situations? are they the same ? #1 : train a model 20 epochs on the whole dataset #2 : divide dataset into n-parts then train the model 20 epochs on each part ...
0
votes
0answers
21 views

Do deep learning researchers generally visualize intermediate steps?

Many researchers in deep learning research come up with new architectures. The architectures are (just) combinations of few existing layers. Along with their mathematical intuition, in general, do ...
0
votes
0answers
13 views

Backpropagation after N sequential input-output pass

I'm trying to train a Neural Network in a particular situation -- similar to a genetic algorithm domain as far as I know. I have to run a simulation with a length of $K$ steps. I have a neural network ...
0
votes
0answers
19 views

When does a batch normalization layer becomes active?

Let us assume your dataset has $n$ training samples each of size $s$ and you divided them into $k$ batches for training. Then each batch has $n_k = \dfrac{n}{k}$ training samples. Batch normalization ...
0
votes
1answer
16 views

Material(s) for understanding “image channels”

I am pretty confused about the concept of "image channels". I want material that explains the concept of channels from scratch to whatever is required to understand their role in machine ...
0
votes
1answer
21 views

How to calculate the gradient penalty proposed in “Improved Training of Wasserstein GANs”?

The research paper titled Improved Training of Wasserstein GANs proposed a gradient penalty in order to avoid undesired behavior due to weight clipping of the discriminator. We now propose an ...
0
votes
0answers
6 views

Is it better to model a Contextual Multi-Armed Bandit problem as an MDP with a non-zero discount factor than treating it as it is?

I'd like to ask if it is, generally, better to model a problem that naturally appears as a Contextual Multi-Armed Bandit like Recommender Systems as an Markov Decision Process with a non-zero discount ...
1
vote
1answer
25 views

How to use a heuristic policy to increase sample efficiency of a deep reinforcement learning agent?

I have a heuristic solution to a problem which works quite well when certain environmental parameters are known and unchanging. However, in a real world setting these parameters will not be known and ...
0
votes
0answers
18 views

Is there a term for performance metric like prediction time on a new/unseen example?

The performance entry on Google's machine-learning glossary doesn't mention prediction time on a new/unseen example which is important for production use. Is there a term to refer to that metric?
0
votes
0answers
11 views

Mapping input vectors of variable length to output vectors of variable lengths with dummy variables

I have a general question about supervised ANNs that map inputs to outputs. It is possible to vary the length of the input and output vectors by inserting some dummy variables that will not be ...
1
vote
2answers
34 views

What is Lipschitz constraint and why it is enforced on discriminator?

The following is the abstract for the research paper titled Improved Training of Wasserstein GANs Generative Adversarial Networks (GANs) are powerful generative models, but suffer from training ...
0
votes
1answer
15 views

Why people always say the Transformer is parallelizable while the self-attention layer still depends on outputs of all time steps to calculate?

When compared to an RNN seq-to-seq model, people always say the Transformer is parallelizable. In the original Attention Is All You Need paper, it also said that Recurrent models typically factor ...
1
vote
1answer
22 views

Creating DQN Learning Agent without Gym environment for a custom project

In a project for college I created a simple turn based game, with up to 4 players that can either move or attack the opponents. The players are playing over the network, meaning the clients are ...
0
votes
0answers
11 views

Is it possible to use a Neural Network to interpolate data [closed]

I am completely new to Artificial intelligence and Neural Networks. I am currently working on a plasma physics simulation project which requires a very high resolution data set. We currently have the ...
3
votes
1answer
216 views

What does “linear unit” mean in the names of activation functions?

Activation functions, in neural networks, are used to introduce non-linearity. Many activation functions that are used in neural networks has the phrase "Linear Unit" in their full form. &...
0
votes
0answers
15 views

random_pad_image color parameter [closed]

I need to perform some data augmentations on my dataset. In TensorFlow models preprocessor.proto I noticed this one, that can be useful in my case: ...
0
votes
0answers
23 views

In general, what are precision, recall, F1 that are reported in papers? [closed]

I used classification_report in sklearn library And, the picture below shows evaluation on my model (anomaly detector) In general, what are precision, recall, F1 ...
0
votes
1answer
29 views

Is my understanding on “smooth approximation” correct?

Consider the following details regarding Softplus activation function $$\text{Softplus}(x) = \dfrac{\log(1+e^{\beta x})}{\beta}$$ SoftPlus is a smooth approximation to the ReLU function and can be ...
0
votes
1answer
26 views

How do I know what a good mean absolute error value is? [closed]

I have just run an MAE calculation for my machine learning models and the results show: SVM MAE = 28.850 deg. Random Forest MAE = 33.832 deg. How do I know what a good MAE value is? What is the ...
0
votes
0answers
12 views

Are there any well-known ways to fuzzy-cluster (variable length) sequences of trajectories?

I have this issue where I need to create 'soft' clusters for different trajectories. The data is sequences of integers where each integer means a specific point; so I have sequences like $s=(1,47,9)$ ...
0
votes
2answers
34 views

What is meant by an axis of a tensor?

Tensor is an ordered collection of elements. The elements are generally real numbers. Tensors are used in deep learning for storing data. There is a wide usage of the word "axis" related to ...
-1
votes
0answers
25 views

Face reconstruction from voice [Limit?]

Speech2Face: Learning the Face Behind a Voice CVPR'19| Speech2Face: Learning the Face Behind a Voice https://speech2face.github.io/supplemental/index.html Is there a good limit for face ...
0
votes
0answers
22 views

Reinforcement learning applicable to a scheduling problem?

I have a certain scheduling problem and I would like to know in general whether I can use Reinforcement learning (and if so what kind of RL) to solve it. Basically my problem is a mixed-integer linear ...
2
votes
3answers
47 views

Why not make the training set and validation set one if their roles are similar?

If the validation set is used to tune the hyperparameters and the training set adjusts the weights, why don't they be one thing as they have a similar role, as in improving the model?
0
votes
1answer
36 views
+100

How to implement a rule-based decision maker for an agent-based model?

I had no idea that there is a stack exchange community for A.I. :-/ So I repost this question here in hope of some guidelines. I tried to delve into the materials discussed in AI: A Modern Approach ...
1
vote
1answer
33 views

Can the optimal learning rate differ for different architectures?

In several courses and tutorials about neural networks, people often say that the learning rate (LR) should be the first hyper-parameter to be tuned before we tweak the others. For example, in this ...
0
votes
0answers
8 views

Compute IoU for each class in Mask R-cnn

I'm trying to compute the IoU, with the matterport Mask R-cnn implementation, for each class (13 in total) that i have in my dataset. For now i managed to compute the average IoU for all the classes ...
1
vote
1answer
24 views

Does “fusion” in “feature fusion” has any formal definition?

I encountered the phrase "fusing features" several times in the literature. I am providing an excerpt from a research paper to provide context for usage of the word fusion. The reason is ...
3
votes
1answer
42 views

What are the necessary mathematical properties to be a loss function in gradient based optimizations?

Loss functions are used in training neural networks. I am interested in knowing the mathematical properties that are necessary for a loss function to participate in gradient descent optimization. I ...
0
votes
1answer
16 views

What is the meaning of R2 appearing as a negative in the RandomForestRegressor?

Machine learning model was created by reading an Excel file where data was stored. I applied RandomForestRegressor to create a model that predicts the size of the sieve particles according to pressure,...
0
votes
0answers
11 views

Deep NN architecture for predicting a matrix from a matrix and list of floats

I am trying to predict a matrix (size RxC) based on an input matrix (size RxC) and a list of floats ...
-1
votes
0answers
17 views

Write $k-$Means as a Genetic Algorithm (Genetic Clustering Algorithm) [closed]

I'm trying to write $k-$Means a genetic algorithm but i'm having trouble with the chromosome representation of the algorithm. I'm thinking in represent $k-$Means as a string (chromosome) with $n$ ...
0
votes
0answers
12 views

Why is the activation function “HardShrink” called so?

Neural networks contain activation functions, which are responsible for the non-linearity of their intermediate and final outputs. Hardshrink is the name of an activation function, which is defined ...
2
votes
0answers
19 views

ReLU function converging to local optimum in one case and diverging in the other one

I implemented a simple neural network with 1 hidden layer. I used ReLU as activation function for the hidden layer and the output layer just uses the linear function. To check my implementation I ...
0
votes
0answers
13 views

Positional Encoding in Transformer on multi-variate time series data hurts performance

I set up a transformer model that embeds positional encodings in the encoder. The data is multi-variate time series-based data. As I just experiment with the positional encoding portion of the code I ...
0
votes
1answer
22 views

An online editor that allows data labeling format

I have a set of students (~20) that will work on annotating data for an NLP project. The annotation task will be as in the following: ...
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 ...
2
votes
1answer
64 views

How to create a neural network from a set of equations?

Say I have these equations: $$x_1 = x_2 + 2y_1 + b$$ $$x_2 = y_2 + c$$ $$y_1 = z + a$$ $$y_2 = y_3 + d$$ $$z = z_1 + e$$ $x_1$ depends on $x_2$ (depends on $y_2$ (depends on $y_3$)) and $y_1$ (depends ...
2
votes
2answers
116 views

Does regularization just mean using an augmented loss function?

We need to use a loss function for training the neural networks. In general, the loss function depends only on the desired output $y$ and actual output $\hat{y}$ and is represented as $L(y, \hat{y})$. ...

15 30 50 per page
1
2 3 4 5
185