# Tag Info

13

What you are looking for is called "reinforcement learning". A reinforcement learning algorithm will try to maximize a reward function. This reward represents how "good" or "bad" an action is in the actual context. For example, in the snake game, your reward will be positive for eating an apple and negative when the snake hits a ...

9

Agent The other answer defines an agent as a policy (as it's defined in reinforcement learning). However, although this definition is fine for most current purposes, given that currently agents are mainly used to solve video games, in the real world, an intelligent agent will also need to have a body, which Russell and Norvig call an architecture (section 2....

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 ...

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

So as you're probably already aware of, CBOW and Skip-gram are just mirrored versions of each other. CBOW is trained to predict a single word from a fixed window size of context words, whereas Skip-gram does the opposite, and tries to predict several context words from a single input word. Intuitively, the first task is much simpler, this implies a much ...

6

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 ...

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: ...

5

A model as a set of functions In some cases in machine learning, a model can be thought of as a set of functions, so here's the first difference. For example, a neural network with an arbitrary vector of parameters $\theta \in \mathbb{R}^m$ is often denoted as a model, then a specific combination of these parameters represents a specific function. More ...

5

In game AI context: An Agent is a player that plays the game. basically, its a function that gets the current state of the game and returns the next action. A Model is a representation of the game. For example, I have made a Gin-Rummy game + AI-agents. One aspect in the model was the representation of the deck as a $4*13$ matrix, where each entry in the ...

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

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 ...

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

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

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 ...

4

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 ...

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 ...

4

I would say that the logic behind the introduction was more empirical than technical. The only difference between LSTM and Bi-LSTM is the possibility for Bi-LSTM to leverage future context chunks to learn better representations of single words. There is no special training step or units added, the idea is just to read a sentence forward and backward to ...

4

Parametric Methods A parametric approach (Regression, Linear Support Vector Machines) has a fixed number of parameters and it makes a lot of assumptions about the data. This is because they are used for known data distributions. i.e, it makes a lot of presumptions about the data Non-Parametric Methods A non-parametric approach (k-Nearest Neighbours, Decision ...

4

There are a few possible approaches to deploying a ML model to a microcontroller. The main limiting factor to deployment on microcontollers is that ML models are usually a representation of a set of parameters that are intended to be used as input to a prediction algorithm alongside a new datapoint. Most such models assume the presence of an accompanying ...

3

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.

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

Consider a continuum of complexity in models. Trivial: $y = x + a$ Simple: $y = x \, \log \, (a x + b) + c$ Moderately complex: A wind turbine under constant wind velocity Very complex: Ray tracing of lit 3-D motion scenes to pixels Astronomically complex: The weather Now consider a continuum regarding the generality or specificity of models. Very ...

3

My guess: If you add a few CNN layers before the input of the given model and train only those layers while keeping the given model's parameters frozen, you might get better result. Essentially these few extra layers would "transform" your input image into the appropriate shape, but with more accuracy since its trained and not hard coded.

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 ...

3

Yes. In Machine Learning we consider that the samples in your training set are sampled from an underlying distribution called the data generating distribution. Generative models classify the samples by trying to learn the distribution of the data. In most cases, either the model is incapable of doing so, or the training samples aren't enough to properly ...

2

One actual example of SAT solvers is finding the set of compatible package versions in python conda package manager. (see, for example, https://www.anaconda.com/blog/understanding-and-improving-condas-performance) The practical applications of SAT solvers involve as well (see http://www.carstensinz.de/talks/RISC-2005.pdf): Product Configuration Hardware ...

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 ...

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