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.

365 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
1
vote
0answers
14 views

Estimating Baselines using ALS

I am trying to figure out how ALS works when minimizing the following formula: $\\ \\$ $\text{min}_{\lbrace b_u,b_i \rbrace} \sum_{(u,i)\in \mathcal{K}} (r_{ui} - \bar{r} - b_u - b_i )^2 + \lambda_{...
1
vote
0answers
42 views

Why do we use the word “kernel” in the expression “Gaussian kernel”?

I've heard the expression "Gaussian kernel" in several contexts (e.g. in the kernel trick used in SVM). A Gaussian kernel usually refers to a Gaussian function (that is, a function similar to the ...
1
vote
0answers
20 views

Is it possible to use AI to find music that have a distinct tune?

Without considering lyrics, there are two type of songs: songs that have a distinct tune which you can easily remember, and songs that are the opposite. Can we design a network to identify the songs ...
1
vote
0answers
19 views

Size of dataset for feature vector with rare event

I'm doing a model to detect duplicate in my database (there is a lot of features that can be different but mean same object in the end) So I have my feature vector for my duplicate dataset which ...
1
vote
1answer
36 views

Do we train a logistic regression model using a dataset that is 3 times bigger than the validation dataset?

Suppose we have a data set $X$ that is split as $X_{\text{train}}$, $X_{\text{val}}$ and $X_{\text{test}}$ and the outcome variable is binary. Let's say we train three different models (logistic ...
1
vote
0answers
15 views

How to combine features with different temporal scale in machine learning

We have various types of data features with different temporal scale. For example, some of them describe the state per second while others may describe the state per day or per month from another ...
1
vote
0answers
37 views

Simple weakly supervised Object localizetion using keras. How to visualize the results?

I am following this link : Weakly-supervised-object-localization to create heatmap of the region in an image where the CNN looks to identify the class. As per the above mentioned repository , ...
1
vote
0answers
48 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
0answers
13 views

Evaluation metrics multi-class classification (ROC- PR curves)

Facing with a multi-class classification task, my question is: are ROC and Precision-Recall (One-vs-All-Rest) curves useful to evaluate and visualize the performance of a model? or Confusion ...
1
vote
0answers
89 views

What are the key differences between cellular neural network and convolutional neural network?

What are the key differences between cellular neural networks and convolutional neural networks in terms of working principle, implementation, potential performance, and applicability?
1
vote
1answer
491 views

How to make meaningful sentences from a set of words?

I have set of topics generated using LDA and like {code, language, test , write, function}, {class, public, method, string, int} etc and I want to make meaningful sentence/sentences from these words ...
1
vote
2answers
83 views

Which algorithm should I use to map an input sentence to an output sentence?

I am new to NLP realm. If you have an input text "The price of orange has increased" and output text "Increase the production of orange". Can we make our RNN model to predict the output text? Or what ...
1
vote
0answers
21 views

Architecture and Use of Different Algorithms for Health Goal Feedback

I wanted to get some opinions from the community for a certain problem that I will be approaching. The problem is to provide feedback to a user based on a image of the upper male torso. The image ...
1
vote
0answers
34 views

How can I generate keywords associated with a website given its URL?

I have a column with links to websites and another column with keywords from those websites. I have to find a map between these two, such that for a new input, which is a website's URL, I can generate ...
1
vote
0answers
14 views

Is there a way to compare the similarities among different graphs and then cluster them using Unsupervised learning?

I have a dataset about (240000,23). For my task, I have to use an unsupervised learning method and apply it on every single column separately in order to detect anomalies that might exist. I have pre-...
1
vote
0answers
51 views

How to translate algorithm from logic to equation, and back?

I just recently got into machine learning, and have been hitting a lot of obstacles understanding the algorithms involved in the programmings. My issue isnt with the programming, but how they're ...
1
vote
0answers
27 views

Automation the import of files to Database

I don't know if this it's possible but nowadays as almost everything is possible I am asking to see if anyone has any idea. The problem is: Regularly I have to import files (CSV, XML, Excel, ...) ...
1
vote
0answers
39 views

Predicting sine using LSTM: Small output range and delayed output?

I have coded a very basic LSTM with forget gates (no libraries used). I'm trying to predict $0.5*sin(t + N)$ given $0.5*sin(t)$ as an exercise. I have tweaked the model, changing the output layer ...
1
vote
0answers
21 views

Any guidance on learning rate / batch size for noisy data (high Bayes error rate)?

Is there any guidance available for training on very noisy data, when Bayes error rate (lowest possible error rate for any classifier) is high? For example, I wonder if deliberately (not due to memory ...
1
vote
0answers
28 views

Why is the learning rate is already very small (1e-05) while the model convergences too fast?

I am training a video prediction model. According to the loss plots, the model convergences very fast while the final loss is not small enough and the generation is not good. Actually, I have test ...
1
vote
0answers
16 views

Azure ML studio pull directly from sharepoint

I am toying around with creating a probability of win calculator for proposals that we do. the information on each proposal is housed in our corporate SharePoint (which I am the admin) Is there a ...
1
vote
0answers
283 views

Experiment shows that LSTM does worse than Random Forest… Why?

LSTM is supposed to be the right tool to capture path-dependency in time-series data. I decided to run a simple experiment (simulation) to assess the extent to which LSTM is better able to understand ...
1
vote
0answers
54 views

GPFlow: Gaussian Process Uncertainty Quantification

I trained some Gaussian process model with the Python library GPFlow on a dataset consisting of $(X, Y)$, inputs and outputs, in a regression setting. This model gives me pretty good predictions in ...
1
vote
0answers
46 views

How do PGMs factor in to modern ML?

I just finished the three-part series of Probabilistic Graphical Models courses from Stanford over on Coursera. I got in to them because I realized there is a certain class of problem for which the ...
1
vote
1answer
132 views

Reduce receptive field size of CNN while keeping its capacity?

I have a convolutional encoder (a CNN) consisting of DenseBlocks and a total of 50 layers (cf. FC-DenseNet103). The receptive field of the encoder (after last layer) is 660 according to Tensorflow ...
1
vote
0answers
12 views

How to use SLAM on other sensor other than camera?

I have a sensor that reads electromagnetic field strength from each position. And the field is stable and unique for each position. So the reading is simply a function of the position like this: <...
1
vote
1answer
27 views

Why PCA works well while the total variance retained is small?

I'm learning machine learning by looking through other people's kernel on kaggle, specifically this Mushroom Classification kernel. The author first applyed PCA to the transformed indicator matrix. He ...
1
vote
0answers
188 views

What are some of the drawbacks of one-shot learning?

One-shot learning seems to work really well in many application domains. Are there any major (or even minor) drawbacks of using one-shot learning? Does it have flaws that could prevent it from being ...
1
vote
1answer
217 views

Why do we need both encoder and decoder in sequence to sequence prediction?

Why do we need both encoder and decoder in sequence to sequence prediction? We could just have a single RNN that, given input $x$, outputs some value $y(t)$ and hidden state $h(t)$. Next, given $h(t)$...
1
vote
0answers
37 views

Train a recurrent neural network by concatenating time series. Is it safe?

As the title says, I want to train a Jordan network (i.e. a particular kind of recurrent neural network) using a certain number of time series. Let's say that $x_1, x_2, \ldots x_N$ are $N$ input ...
1
vote
1answer
71 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 ...
1
vote
0answers
36 views

Unbalanced dataset in regression rather than classification

Assume that we have a labeled dataset with inputs and outputs, where the output range is $\left[0, 2\right]$, but the majority of outputs is in $\left[0, 1\right]$. Should one adopt some kind of over- ...
1
vote
0answers
36 views

Detect root cause across many event occurrences

Suppose there are sensors which supply numerical metrics. If a metric goes above or below healthy threshold, an event (alert) is raised. Metrics depend on each other in one way or another (we can ...
1
vote
0answers
20 views

How exactly is equivariance achieved in capsule networks?

I have read quite a lot about capsule networks but cannot understand how the squashed vector would also rotate in response to rotation or translation of the image.A simple example would be helpful.I ...
1
vote
0answers
55 views

First perceptron learning algorithm

I struggle to find Rosenblatts perceptron training algorithm in any of his publications from 1967 - 1951, namely: [1] Principles of Neurodynamics: Perceptrons and the Theory of Brain Mechanisms [2] ...
1
vote
0answers
29 views

Pre priming a network for white space

When a human looks at a page. He notices the sets of letters are grouped together separated by white space. If the white space was replaced by another character say z, it would be harder to ...
1
vote
0answers
57 views

Reinforcement learning for segmenting the robot path to reflect the true distances

I've a grid of rectangles acting as blocks. The robot traverses through the inter-spaces between these consecutive blocks. Now I have sensor data streaming in representing Right and left wheel speeds. ...
1
vote
3answers
357 views

How to create Partially Connected NNs with prespecified connections using Tensorflow?

I'd like to implement a partially connected neural network with ~3 to 4 hidden layers (a sparse deep neural network?) where I can specify which node connects to which node from the previous/next layer....
1
vote
0answers
19 views

How to handle Feature changes in a model deployed ?

I implemented and deployed with Flask an XGBoost model for a classification problem. But being aware that features importance can change over time to predict probability of label for new data, I ...
1
vote
0answers
96 views

Can semantic paraphrasing be used for a workflow management system?

The term paraphrasing is used for converting input text into output text with small modifications on the semantic level. Paraphrasing is used by managers to distribute work items to employees. It is a ...
1
vote
0answers
336 views

Why do we need Upsampling and Downsampling in Progressive Growing of Gans

I was working recently on Progressive Growing of GANs (aka PGGANs). I have implemented the whole architecture, but the problem that was ticking my mind is that in simple GANs, like DCGAN, PIX2PIX, we ...
1
vote
0answers
183 views

How does the target output of a Single Shot Detector (SSD) look like?

According to the paper SSD: Single Shot MultiBox Detector, for each cell in a feature map k boxes are acquired and for each box we get $c$ class scores and $4$ offsets relative to the original default ...
1
vote
0answers
44 views

How recurrent neural network work when predict many days?

I use recurrent neural network, RNNs have to get input one value per step and it will show one value output. If I have daily sale demand time series data. I want to predict sale demand for three ...
1
vote
0answers
42 views

Optimization step in Apprenticeship Learning via Inverse Reinforcement Learning

Why the optimization step of the algorithm a quadratic program? [See: Apprenticeship Learning via Inverse Reinforcement Learning; page 3] Isn't the objective function linear? Why don't we treat ...
1
vote
0answers
26 views

Difference in trained models between GCP's Google Vision and Firebase's ML kit?

Anyone here know if the image-recognition/text-recognition/etc features of Google Vision API use the same trained models as the image-recognition/text-recognition/etc of Firebase's ML kit? If they don'...
1
vote
0answers
36 views

What methods are there to detect discrimination in trained models?

I've been researching AI regulation and compliance (see my related question on law.stackexchange), and one of the big take-aways that I had is that the regulations that apply to a human will apply to ...
1
vote
0answers
26 views

In CNN (Convolutional Neural Network), does the combination of previous layer's filters make next layer's filters?

I know that the first layer uses a low-level filter to see the edge information. As the layer gets deeper, it will represent high-level (abstract) information. Is it because the combinations of ...
1
vote
0answers
46 views

small multinomial Naive Bayes text classification probabilities

When applying multinomial Naive Bayes text classification I get very small probabilities(around 10e-48) so there's no way for me to know which classes are valid ...
1
vote
0answers
64 views

How do GAN's generator actually work?

I have implemented DCGAN's myself and have been studying GAN's for over a month now. Now I am implementing the pggans but I encountered a sentence When we measure the distance between the ...
1
vote
0answers
56 views

Why do we have to solve MDP in each iteration of Maximum Entropy Inverse Reinforcement Learning?

Gradient in Maximum Entropy IRL requires to find the probability of expert trajectories given the reward function weights. This is done in the paper by calculating state visitation probabilities but I ...