Questions tagged [machine-learning]

For questions related to machine learning (ML), which is a set of methods that can automatically detect patterns in data, and then use the uncovered patterns to predict future data, or to perform other kinds of decision making under uncertainty (such as planning how to collect more data). ML is usually divided into supervised, unsupervised and reinforcement learning. Deep learning is a subfield of ML that uses deep artificial neural networks.

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

When using experience replay in reinforcement learning, which state is used for training?

I'm slightly confused about the experience replay process. I understand why we use batch processing in reinforcement learning, and from my understanding, a batch of states are input into the neural ...
1
vote
1answer
51 views

How to solve the “dangerous feedback loops” in machine learning?

From the article Dangerous Feedback Loops in ML Let’s say our model has leads from Facebook, Google, and Bing. If our first model decides that the probability of conversion is 3%, 5%, and 1% from ...
4
votes
2answers
2k views

What is the purpose of “reshaping it into the shape the network expects and scaling it so that all values are in the [0, 1] interval.”?

I am a deep learning beginner recently reading this book "Deep learning with Python", the example explains the process of implementing a greyscale image classification using MNIST in keras, in the ...
0
votes
1answer
110 views

What is Bayes' theorem?

What is Bayes' theorem? How does it relate to conditional probabilities?
1
vote
3answers
65 views

How does batch normalisation actually work?

I actually went through the Keras' batch normalization tutorial and the description there puzzled me more. Here are some facts about batch normalization that I read recently and want a deep ...
0
votes
2answers
255 views

What is the proof behind the gradient of a curve being proportional to the distance between the two co-ordinates in the x-axis?

In the [delta rule][1] the equation to adjust the weight with respect to error is $$w_{(n+1)}=w_{(n)}-\alpha \times \frac{\partial E}{\partial w}$$ *where $\alpha$ is the learning rate and $E$ is the ...
1
vote
1answer
51 views

Binary mode or Multi-label mode is correct when using binary crossentropy and sigmoid output function on multi-label classification

I would like to ask a question about the relationship of accuracy with the loss function. My experiment is a multiclass text classification problem, and I have built a Keras neural network to tackle ...
10
votes
1answer
109 views

Will parameter sweeping on one split of data followed by cross validation discover the right hyperparameters?

Let's call our dataset splits train/test/evaluate. We're in a situation where we require months of data so we prefer to use the evaluation dataset as infrequently as possible to avoid polluting our ...
3
votes
1answer
65 views

How to use text as an input for a neural network - regression problem? How many likes/claps an article will get

I am trying to predict the number of likes an article or a post will get using a NN. I have a dataframe with ~70,000 rows and 2 columns: "text" (predictor - strings of text) and "likes&...
0
votes
0answers
28 views

Monte Carlo Tree search UCB1 for Tic-Tac-Toe help

I am trying to code a MCTS agent for tic tac toe and i have some theoretical questions regarding MCTS. 1)I am using the UCB1 MCTS $UCB(Si)=average value + 2*sqrt(ln(N)/ni)$ . Considering the image ...
1
vote
1answer
56 views

Understaning Bayesian Optimisation graph

I came across the concept of Bayesian Occam Razor in the book Machine Learning: a Probabilistic Perspective. According to the book: Another way to understand the Bayesian Occam’s razor effect is ...
0
votes
0answers
21 views

How Discriminator and Generator weights are adjusted in conditional Generative adversarial networks proposed by Isola et al. ? (in simple terms)

Can someone please explain to me the complete architecture of cGANs as mentioned here. I am confused as "ref" is not defined in the whole article. I am sorry if you find the question silly. ...
3
votes
1answer
100 views

How can I train a neural network to grade the user's answers to a questionnaire?

I have a questionnaire consisting of over 10 questions. The questionnaire is being answered by a lot of people, which I have manually graded. Each question can give the user up to 10 points depending ...
5
votes
1answer
115 views

Which Rosenblatt's paper describes Rosenblatt's perceptron training algorithm?

I struggle to find Rosenblatt's perceptron training algorithm in any of his publications from 1957 - 1961, namely: Principles of Neurodynamics: Perceptrons and the Theory of Brain Mechanisms The ...
0
votes
1answer
27 views

How do I classify whether a document is legal or not given a set of keywords that appear only in legal documents?

Let's say that I want to classify whether a document is a legal document or not. I have a list of keywords that will be presented only in legal documents. What is the proper way or algorithm to ...
1
vote
1answer
48 views

Is it possible that every class has a higher recall than precision for multi-class classification?

I am a student learning machine learning recently, and one thing is keep confusing me, I tried multiple sources and failed to find the related answer. As following table shows (this is from some paper)...
1
vote
2answers
62 views

Why the cost/loss starts to increase for some iterations during the training phase?

I am trying to build a recurrent neural network from scratch. It's a very simple model. I am trying to train it to predict two words (dogs and gods). While training, the value of cost function starts ...
0
votes
0answers
9 views

Finding Cycles in a State Sequence

Suppose I observe a set of states $\mathbf{X} = \{X_{1}, X_{2}, \ldots, X_{K}\}$ over time. I assume that there exist $M$ cycles $\mathbf{C} = \{C_{1}, C_{2}, \ldots, C_{M} \}$ in the observed state ...
0
votes
0answers
37 views

Is it a good idea to change the learning rate at each training step as a function of the loss?

Is it a good idea to change the learning rate at each training step as a function of the loss? i.e. for points with high loss value, put a high learning rate and for low loss value a low learning rate ...
3
votes
2answers
59 views

Are there any easy ways to create annotated training images for object detection?

For the purposes of object detection, are there any easy ways to create annotated training images? For example, if we have $10,000$ images and want to draw bounding boxes on 2 objects for each image, ...
-1
votes
0answers
20 views

How to enable transfer learning for Stylegan2 Tensorflow model training? [closed]

I am working in Google Colab with StyleGAN2 and need to transfer learning from a pre-trained model, for better quality with a small dataset and for reducing of training time. There is a file "...
1
vote
1answer
110 views

Why should each filter have different weights for each input channel?

From the answers to this question In a CNN, does each new filter have different weights for each input channel, or are the same weights of each filter used across input channels?, I got the fact that ...
-1
votes
0answers
28 views

Training a Neural Network with Hexadecimal input

I currently started working in the field of Machine Learning and have been stuck on a problem where I have to train a Neural Network with a dataset containing hexadecimal inputs. I found that we can ...
7
votes
3answers
2k views

What is the relation between semi-supervised and self-supervised visual representation learning?

What's the differences between semi-supervised learning and self-supervised visual representation learning, and how they are connected?
0
votes
1answer
36 views

Best ways of leveraging AI for stock market trading

What are the current popular approaches to leveraging AI for stock price prediction? It seems like there could be several approaches and problem formulations: Supervised learning: Regression: ...
1
vote
0answers
23 views

Can I use ML to discover via videos the best place to shoot in foosball?

I am a programmer, but just now attempting to enter the world of ML. I'm eyeballing a potential project/problem related to foosball. Pro foosball is a thing believe it or not and I'm wondering if I ...
2
votes
0answers
57 views

How can I find a specific word in an audio file?

I'm trying to train and use a neural network to detect a specific word in an audio file. The input of the neural network is an audio of 2-3 seconds duration, and the neural network must determine ...
1
vote
1answer
39 views

How to generate labels for self-supervised training?

I've been reading a lot lately about self-supervised learning and I didn't understand very well how to generate the desired label for a given image. Let's say that I have an image classification task, ...
4
votes
1answer
92 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 ...
1
vote
1answer
59 views

Facial Recognition + Database + Compare & Identify - is it complicated?

The last week I've been looking for freelancers who are able to do this project for me but they weren't that experienced in it, so I would like to know whether my idea is complicated or is it their ...
2
votes
1answer
101 views

Why is this ResNet50 misclassifying objects?

I'm new to Deep Learning, and I have some conceptual problems. I followed a simple tutorial here, and trained a model in Keras to do image classification on 10 classes of logos. I prepared 10 classes ...
40
votes
3answers
31k views

What is self-supervised learning in machine learning?

What is self-supervised learning in machine learning? How is it different from supervised learning?
0
votes
0answers
21 views

Finding whether an input column is missing

I am working on a problem similar to this one:(supervised, artificial data) ...
15
votes
1answer
968 views

Are information processing rules from Gestalt psychology still used in computer vision today?

Decades ago there were and are books in machine vision, which by implementing various information processing rules from gestalt psychology, got impressive results with little code or special hardware ...
0
votes
1answer
42 views

Is gradient descent scale invariant or not?

I know we should scale the input and output (assuming regression task) before we feed it to the neural network. Then the gradient descent will give the better minima much faster. But I have subtle ...
1
vote
1answer
60 views

Pros and Cons of Seq2Seq vs Bidirectional RNN

It seems to me that Seq2Seq models and Bidirectional RNNs try to do the same thing. Is that true? Also, when would you recommend one setup over another? Thanks!
-1
votes
0answers
60 views

Is GPT-3 better than what DeepMind could do? [closed]

So there is this tremendous hype about GPT-3, which is in fact impressive. But I've been always convinced that DeepMind was by far the leader in machine learning. However, I didn't find any comparable ...
1
vote
1answer
49 views

How is the probability transition matrix populated in the Markov process (chain) for a board game?

Following on from my other (answered) question: With regards to the Markov process (chain), if an environment is a board game and its states are the various position the game pieces may be in, how ...
1
vote
0answers
49 views

What is the best way to make a deep reinforcement learning environment with a continuous 2D action space?

I understand that the actor-critic method is probably where I want to start because of how it works with continuous action spaces. However, the problem I am trying to solve would require the action be ...
2
votes
1answer
111 views

What is the input for the prior model of VQ-VAE?

I'm trying to implement the VQ-VAE model. In there, a continuous variable $x$ is encoded in an array $z$ of discrete latent variables $z_i$ that are mapped each to an embedding vector $e_i$. These ...
1
vote
3answers
122 views

Who is working on explaining the knowledge encoded into machine learning models?

The thing about machine learning (ML) that worries me is that "knowledge" acquired in ML is hidden: we usually can't explain the criteria or methods used by the machine to provide an answer ...
1
vote
1answer
292 views

What is the best machine learning algorithm to select best 3 variable combinations?

I have 10 variables as like below V1=1, V2=2, V3=3, V4=4, V5=5, V6=6, V7=7, V8=8, V9=9 and V10=10 Note : Each variable can have any value Now I want to select the best 3 variables combination as ...
1
vote
1answer
71 views

Does this $\max$ mean that we need to maximize the regret in this regret formula?

I found that the regret in Online Machine Learning is stated as: $$\operatorname{Regret}_{T}(h)=\sum_{t=1}^{T} l\left(p_{t}, y_{t}\right)-\sum_{t=1}^{T} l\left(h(x), y_{t}\right),$$ where $p_t$ is the ...
2
votes
1answer
68 views

Can a fully convolutional network always return an image of the same size as the original?

I'm trying to perform a segmentation task on images of multiple sizes using fully convolutional neural networks. Currently, I'm using EfficientNet as a feature extractor, and adding a deconvolution/...
2
votes
1answer
66 views

why the sigmoid function will be 1 and 0 if we use a fully connected layer that produce a big enough positive(res negative )output

I am using a fully connected neural network that uses sigmoid activation function. If we feed a big enough weights the sigmoid function will finally become 1 or 0, is there any solution to avoid this? ...
0
votes
1answer
33 views

Is there a relationship between the response and predictors?

I have been reading introduction to statistical learning, and I was going through multiple linear regression. This is the topic that I'm reading: As I was reading further, I encountered an equation ...
2
votes
1answer
89 views

Price difference predictions curve almost vanished

With a team, we are studying how it is possible to predict the price movement with high-frequency. Instead of predicting the price directly, we have decided to try predicting price difference as well ...
4
votes
1answer
95 views

Will BERT embedding be always same for a given document when used as a feature extractor

When we use BERT embeddings for a classification task, would we get different embeddings every time we pass the same text through the BERT architecture? If yes, is it the right way to use the ...
5
votes
3answers
156 views

Why is symbolic AI not so popular as ANN but used by IBM's Deep Blue?

Everybody is implementing and using DNN with, for example, TensorFlow or PyTorch. I thought IBM's Deep Blue was an ANN-based AI system, but this article says that IBM's Deep Blue was symbolic AI. Are ...
3
votes
2answers
70 views

How can I predict the true label for data with incomplete features based on the trained model with data with more features?

Suppose I have a model that was trained with a dataset that contains the features (f1, f2, f3, f4, f5, f6). However, my test dataset does not contain all features ...

1
2 3 4 5
32