Questions tagged [machine-learning]

Theoretical questions about Machine learning, especially Computational Learning Theory, including Algorithmic Learning Theory, PAC learning, and Bayesian Inference

Filter by
Sorted by
Tagged with
-3
votes
1answer
134 views

Semi-supervised learning on graphs

What is semi-supervised learning on graphs? We have been told that if we just have a function which has an input graph, or a given graph with labeled nodes, we should be able to predict labels on ...
-3
votes
0answers
28 views

Algorithm to decide percentage of data from previous node, current node and forward nodes

I have a graph-like structure, let's say there is one node $C$, who has 2 predecessors $A,B$ and 1 successor $D$. I have a value of $C$. Let's say value at $C=30$%. From this, I could infer that I ...
-3
votes
1answer
553 views

Mapping input and output sequences using neural networks in high dimensional data

I have this huge dimensional data with 31200 features and only 6000 examples. I want to learn a neural network that can find the non linear relation between the input and outputs. However, I have ...
-3
votes
1answer
224 views

Which algorithm for a project about online machine learning?

I have a basic understanding of how machine learning works, but my knowledge isn't enough in order to develop a personal project I would like to start. I want to develop a system based on online ...
-4
votes
0answers
32 views

What to choose Deep learning or Artificial Intelligence after learning basic Machine Learning? [closed]

I Learned basics from Machine Learning and its algorithm and I wanted to choose the on subject from deep learning and artificial neural network so I am confused which one to choose can any one guide ...
-4
votes
1answer
2k views

Find sentences with similar relative meaning from a list of sentences against an example one

I want to be able to find sentences with the same meaning. I have a query sentence, and a long list of millions of other sentences. Sentences are words, or a special type of word called a symbol which ...
-5
votes
0answers
47 views

If machine learning can cover any CS problem, wouldn't it prove that P=NP? [closed]

My (naive) comprehension is that any CS problem, both P and NP, could be expressed as a set of data to expose to ML computation. It doesn't matter how much time the ML algorithm would take to learn ...

1
3 4 5 6
7