# Tag Info

13

Things in italics should give you enough googleable terms to start a deeper dive :P. There are 3 main branches of statistical ML. Supervised Learning This approach is taken when a problem can be phrased as associating some $X$ with some $Y$. For example, classifying a picture of a cat ($X$) with the label “Cat” ($Y$). Training in supervised learning usually ...

11

No, GANs are not used. It's reinforcement learning at what it does best. The tree search is an interesting addition and assists with navigating the sheer scale of the game. Although the agent was playing itself to become better, there wasn't 2 separate networks (generator and discriminator). The agent learned through RL and didn't have the error ...

9

Correlation Between Entries The first recommendation is to ensure that appropriate warning and informational entries in the log file are presented along with errors into the machine learning components of the solution. All log entries are potentially useful input data if it is possible that there are correlations between informational messages, warnings, ...

8

Supervised learning is typically an attempt to learn a mathematical function, $f(\bf X)=\bf y$. For this, you need both the input vector $\bf X$ and the output vector $\bf y$. The model outputs have whatever dimensionality that the target values have. Unsupervised learning models instead learn a structure from the data. A clustering model, for example, is ...

6

Neural networks don't model biological neurons. They are at best inspired by biological neurons, in that they get excited by certain inputs and fire once the excitation crosses a threshold. And this second point even holds only approximately because the backpropagation algorithm needs smoothed out steps to learn by gradient descent. And backpropagation is ...

5

I disagree with the context that MNIST is the "hello world" of supervised learning. It is definitely, though, the "hello world" of image classification, which is a very specific sub-field of supervised learning. I'd consider the Iris dataset a better candidate for the "hello world" of supervised learning, with other close ...

4

In graph clustering, we want to cluster the nodes of a given graph, such that nodes in the same cluster are highly connected (by edges) and nodes in different clusters are poorly or not connected at all. A simple (hierarchical and divisive) algorithm to perform clustering on a graph is based on first finding the minimum spanning tree of the graph (using e....

4

So if I understood correctly: You have data from 2 sensors in time: Ar flow and BackGas Flow (SCCM, what is that?) You have that data for multiple products. 1 - Since it is relatively low dimensional, you may try using raw data with K-Means or Self Organizing Maps. 2 - If you searching for anomalies in time, you might try using feature engineering with ...

3

I found the following detailed and well documented Python notebook, which uses only NumPy.

3

If your anomalies are simply peaks, why should you be using machine learning methods? You could use peak detection algorithms for the purpose. If you still insist on ML, isolation forest is a good try.

3

There is a problem with confining Artificial Intelligence to a single definition, because it has become an umbrella term encompassing many fields of science. It has come a long way from the "thinking machines" of the 50s. Actually, the term was coined in a summer workshop in 1956, whose proposal was: The study is to proceed on the basis of the conjecture ...

3

Supervised learning The supervised learning (SL) problem is formulated as follows. You are given a dataset $\mathcal{D} = \{(x_i, y_i)_{i=1}^N$, which is assumed to be drawn i.i.d. from an unknown joint probability distribution $p(x, y)$, where $x_i$ represents the $i$th input and $y_i$ is the corresponding label. You choose a loss function \$\mathcal{L}: ...

3

In Supervised learning, the goal is to learn a mapping from points in a feature space to labels. So that for any new input data point, we are able to predict its label. whereas in Unsupervised learning data set is composed only of points in a feature space, i.e. there are no labels & here the goal is to learn some inner structure or organization in the ...

2

Unsupervised pre-training was done only very shortly, as far as I know, at the time when deep learning started to actually work. It extracts certain regularities in the data, which a later supervised learning can latch onto, so it is not surprising that it might work. On the other hand, unsupervised learning doesn't give particularly impressive results in ...

2

The GA will require a fitness function, which means you need labeled data for comparison. That conclusion is wrong. Yes, sometimes your fitness function will use labeled data. For example, if you want to train an XOR gate or any other known function. However, there is arguably no advantage of training a function with neuroevolution versus backpropagation, ...

2

By the way you have explained things above, it seems more like a problem with your code and not the something to do with the environment. The term discrete and continuous is used to define, how the outside environment is acting, rather than how your code is taking its steps. These are some lines from the book, Artificial Intelligence: A Modern Approach: ...

2

You're basically looking for is unsupervised learning (UL). There are a lot of UL techniques around, but I'm not sure you'll find one that does exactly what you want with no user input at all. Still, if you skim the literature on these approaches, you may well find something useful. One option is DBSCAN, a very popular clustering algorithm that does not ...

2

Adding to SmallChess's answer , Larger trees(with many nodes) are too adapted to the training set, as a small change in the input train data might cause the trees to change very much and hence change the estimate value too much.This is mainly due to the hierarchical structures of trees(because a change in a higher node may cause all lower nodes to change). ...

2

The bigger your tree is the more overfitting your model is. In machine learning, we always prefer a simpler model unless there is good reason to go for complication.

2

Although there doesn't seem to be standardization of the terminology involving assisted learning, I've been noticing this concept, and the distinction, popping up in articles recently, surely driven by important milestones in unassisted machine learning. My understanding is that Algorithmic Intelligence has traditionally been based on complex decision-...

2

You should look into unsupervised learning, which is machine learning without a human-labeled training set.

2

I wrote a relatively simple adaptive parser in Prolog. The parser is essentially a string rewriting system that learns new rewrite rules from its input, such as "A implies that B" means "A implies B", or "neither A nor B" means "not (A or B)", using a simple bottom-up parsing algorithm. Using the grammar rules that it has learned, the parser is able to ...

2

Neural networks are not inherently part of reinforcement learning (a popular agent-based framework for describing control problems). In general, if you have an agent-based scenario, you are trying to optimise a function: Policy( State ) -> Action Where State can be any combination of current observations and history that seem relevant to the problem. ...

2

Answer is quite yes, please have a look what Google did around this: Google Cloud Video Intelligence makes videos searchable, and discoverable, by extracting metadata with an easy to use REST API. You can now search every moment of every video file in your catalog. It quickly annotates videos stored in Google Cloud Storage, and helps you identify key ...

2

Yes! Unsupervised machine learning has absolutely been applied to youtube videos... To recognize cats! Here's an article about it in wired. One of the leading ML researchers was Andrew Ng.

2

Yes, it is possible, and yes, it probably has been done before. Odds are, however, the person(s) who tried were disappointed with the results and forgot to tell others. The reasons they might be disappointed could be any of the following: Took to long to train Even when fully trained, (or appeared to be), it did not give the expected output Too sensitive ...

2

The processing power might still follow the Moore's law, but it is basically an economical law, although it has worked surprisingly well considering the physical limitations of technology. An Artificially Intelligent agent could focus on manipulating the market, research possible hardware improvements, allocate human resources more effectively to the problem,...

2

AI will only "evolve" selfishness if it "evolves" in a competitive environment and has certain human-like faculties. Self-protecting desires on the other hand are logical consequences of having any goal at all. After all, you can't reach your goal if you are destroyed. The concern of "evil" super intelligences isn't that they literally turn evil and ...

2

Could you please let me know which of the following classification of Neural Network's learning algorithm is correct? The first one classifies it into: supervised, unsupervised and reinforcement learning. Those three forms of Machine Learning are not really different forms of a Neural Network learning algorithm (or, really, any ...

2

I believe that the idea is to have a similar ratio of fraud/"normal transaction" as to the ones that bank encounter on real life. If you balance it you will probably have a lot of false positive once you apply your solution to real world's data and, if that may be fine for you to play with, it's not what a bank would like as they can't block too much of the ...

Only top voted, non community-wiki answers of a minimum length are eligible