Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 5 years ago.
Improve this question
I want to train an output vector(which is from deep learning model) like fixed vector. Hence, I chose a cosine similarity between two vectors as the objective function. However, I don't know if that is a correct approach for my need.
No. The cosine similarity is a measure of how similar two items (samples in your dataset) are.
In contrast, the objective function when training a neural network should be a definition of the current estimation error over the data - so they are different things.
Related
Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 2 days ago.
Improve this question
I've been working on this project for a bit and would like to know which approach is the best out of the two that I have come up with. My project is about the weight of a potato.
Keep in mind it takes a lot of time and resources to record data.
Approach One
use a computer vision algorithm to find the height of an object. And since that height and weight have a linear relationship with a potato. We can use a linear regression model to figure out the weight of the object
Approach Two
collect a dataset of images of potatoes with their corresponding weights and preprocess the data using YOLO. Through this we can get the weight of the object.
Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 2 years ago.
Improve this question
Can someone please give me some suggestions on which feature selection techniques for gene classification should I use?
The major problem to work with gene expression data, with a large number of dimensions and small sample size. Instead of standard feature extraction/selection algorithms, generally, kernel-based feature selection algorithms are applied to gene expression data such as KBMTL(kernelized Bayesian multitask learning), NDR(nonlinear dimensionality reduction) or regularized linear methods such as LASSO and Elastic-net.
You can check these papers to learn more about how to make efficient feature selection on gene expression data.
paper1
paper2
paper3
Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 3 years ago.
Improve this question
I am looking for the machine learning correct approach for predicting the lottery numbers, not the most accurate answer but at least we have some predicted output. I am implementing the regression based and neural network models for this. Is their any specific approach which follows this?
It is impossible. The lottery numbers are random - actually to be more specific, the system is chaotic. You would require the initial configuration (positions etc) to insane (possibly infinite) precision to be able to make any predictions. Basically, don't even try it.
Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 4 years ago.
Improve this question
Can feature selection algorithms in Scikit-Learn or in other machine learning python modules be used with categorical values in dataset?
Not directly. If your column is categorical, you need to encode it
into numerical representation. If your column consist of textual entries, you would first need to transform this text into numerical vectors - check bag of words or tf-idf for example.
Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 4 years ago.
Improve this question
i am stuck with this problem. I have generated handwritten digit using GANs. And now I want to evaluate how accurate my generated handwritten digits are. Is there any way??
The most common ways to evaluate the network is to either show the visual output as in the original gan paper (http://papers.nips.cc/paper/5423-generative-adversarial-nets) or by showing on how well they do for semi-supervised learning (http://papers.nips.cc/paper/6125-improved-techniques-for-training-gans.pdf). This means using GANs to improve classification performance for the case, where only little data is available .