Hot answers tagged

8

"Current artificial intelligence research" is a pretty broad field. From where I sit, in a mostly CS realm, people are focused on narrow intelligence that can do economically relevant work on narrow tasks. (That is, predicting when components will fail, predicting which ads a user will click on, and so on.) For those sorts of tools, the generality of a ...


7

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

This answer applies to Machine Learning (ML) part of AI, as that seems to be what you are asking about. Please bear in mind that AI is still a broad church, including many other techniques than ML. ML, including neural networks for deep learning, and Reinforcement Learning (RL) is only a subset of AI - some AI techniques are more focused on the algorithm ...


5

Using a machine learning or AI-powered model once it has been built and tested, is not directly an AI issue, it is just a development issue. As such, you won't find many machine learning tutorials that focus on this part of the work. But they do exist. In essence it is the same as integrating any other function, which might be in a third-party library: ...


4

One good way of differentiating modelling and implementation is to consider that models occupy a much higher level of abstraction. To continue with the mathematical example: even though experimental mathematics might be dependent on computation, the program can be considered as one possible realization of the necessary conditions of a more abstract ...


4

This article gives a description of mirror neurons in terms of Hebbian learning, a mechanism that has been widely used in AI. I don't know whether the formulation given in the article has ever actually been implemented computationally.


4

Is AIXI really a big deal in artificial general intelligence research? Yes, it is a great theoretical contribution to AGI. AFAIK, it is the most serious attempt to build a theoretical framework or foundation for AGI. Similar works are Schmidhuber's Gödel Machines and SOAR architecture. AIXI is an abstract and non-anthropomorphic framework for AGI which ...


4

AIXI is really a conceptual framework. All the hard work of actually compressing the environment still remains. To further discuss the question raised in Matthew Graves answer: given our current limited level of ability to represent complex environments, it seems to me that it doesn't make a lot of practical difference whether you start with AIXI as ...


4

It depends on what exactly you want to be. You don't need to be mathematician if you just want to run neural networks. Most data scientists don't understand the mathematics, but they know how to run machine learning frameworks. Generally, only PhDs understand the mathematics. In the industry, most job positions in machine learning (e.g software engineer, ...


4

What are the trained models? are they algorithms or a collection of parameters in a file? "Model" could refer to the algorithm with or without a set of trained parameters. If you specify "trained model", the focus is on the parameters, but the algorithm is implicitly part of that, since without the algorithm, the parameters are just an arbitrary set of ...


3

We can already observe information bubbles on social media, where the circle is that machine learns what content people like and give more similar content based on clicks and so on. From single wrong click you could enter a bubble and never come out if you don't take care or be aware. This happens with humans, so same may apply to computers. Checking ...


3

I think your net should have the various actions as outputs, but I am not an expert in Deep Nets. I just think that that light form of multi-task learning might be better. The idea of multi-task learning is that a predictor predicting multiple variables (in this case the various Q(s,a1), Q(s,a2), ...) using mostly the same structure (varying only the output ...


3

In AI (but in general too, I believe), a simplification is that modeling is more akin to Mathematics (and related hard sciences involved, like Physics and... Computer Science), and implementation to Software Engineering. Let's take a concrete example, really outside of AI: Find the minimum value of a given polynomial, if it exists. The Mathematician will ...


3

From what I understand, Monte Carlo Tree Search Algorithm is a solution algorithm for model free reinforcement learning (RL). Monte Carlo Tree Search is a planning algorithm. It can be considered part of RL, in a similar way to e.g. Dyna-Q. As a planning algorithm MCTS does need access to a model of the environment. Specifically it requires a sampling ...


3

Whether or not MCTS is even a Reinforcement Learning algorithm at all may be up for debate, but let's assume that we view it as an RL algorithm here. For practical purposes, MCTS really should be considered to be a Model-Based method. Below, I'm going to describe how you could view it as a Model-Free RL approach in some way... and then wrap back to why that ...


3

No. This is currently out of the scope for any language processing system. It requires a general understanding of abstract concepts which is not possible for machines at present. In order to recognise a self-fulfilling prophecy, you first need to identify that something is a prophecy. So it needs to be something that expresses a possible future state, for ...


2

Instead of talking about just SAT solvers, let me talk about optimization in general. Many economic problems can be cast as optimization problems: for example, FedEx may have a list of packages and the destinations for those packages, and must decide which packages to put on which trucks, and what order to deliver those packages in. If you write out a ...


2

A model is exactly what the name suggests. A simplified representation of a solution to a real life problem. For example, if you think of a simple formula for a falling object you may not take into account real life variables such as the imperfections on the surface of the object, atmospheric conditions, the exact composition of the air the object is ...


2

You can flatten the graph into a matrix and then train it like a normal neural network input. Perhaps an adjacency graph or maybe simply a series of linear equations representing the nodes and convert it into matrix form.


2

Well simply put AI model can be seen just as a flowchart showing how the control flow moves where it moves how it moves why it moves etc. However AI architecture refers to the next step after building an AI model AI architecture involves representation of the functions that you use in your program. It also involved declaration of the variables you're going ...


2

Architecture describes a general approach to a ML problem, and the parameterization of that approach. For example, a neural net architecture would define the number and size of different layers, the type of each layer, and so on. A model is one specific instance of a given architecture, trained on a given dataset. For the example of neural nets, the model ...


2

AI is a two step process: use data to learn a model, and then use the model to make predictions using new data. So an AI model is the result of the learning process, and the architecture is the detail of how the learning is achieved.


2

It mostly seems to be a personal preference type of thing. But in my readings, AI architecture typically means a large scale structural difference (connectionist / GOFAI; deep stack / recurrent, while AI models are finer distinctions between methods in a common architecture (say, the AlexNet vs other CNNs)


2

Mathematical models are essentially highly formalised knowledge. When it comes to computer engineering, there is literally no other choice - anything you can write code for, or design a machine for, will have an associated mathematical model. That model may not be fully explored or comprehended analytically by theorists, it may be just too complex (and ...


2

I haven't seen any dataset where some standard models worked and neural networks utterly failed. For columnar data (e.g. Excel files / database dumps / CSV files) which contain structured data usually tree-based models like random forests and gradient boosting work better, but neural networks are also usually way better than random. If you demand other ...


2

Begin by learning the mathematical treatments at their foundations. Game theory pioneered John von Neumann and Oskar Morgenstern Information theory pioneered by Claude Shannon (Bell Labs) Incompleteness pioneered by Kurt Gödel (which led to Alonso Church's lambda calculus and Turing's completeness which led to a general criteria that defines what a ...


2

This sounds like a great project, although this exact setup limits your options somewhat. Supervised machine learning approaches are effectively ruled out because you don't have the necessary training data to develop a model (i.e. the dependent variable: whether it is raining or not). You could look at accessing similar data (from what source depends on ...


2

A RBM (restricted Boltzmann machine) can be trained to extract document features. The same resulting machine can extract features of two or more documents. Because documents can be just as easily processed in series using the same machine parameters and CPU (saving the feature results) as documents could be processed in parallel using separate CPUs, the ...


2

I believe, this post and this post written by me well address your question. EDIT In fact, this is a very interesting question that you ask. It deserves some more explanation. 1. Fully connected networks The more layers you add, the more "nonlinear" your network becomes. For instance, in the case of two spirals problem, which requires a "highly nonlinear ...


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