13 votes
Accepted

Is there a machine learning model that can be trained with labels that only say how "right" or "wrong" it was?

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 "...
kirua's user avatar
  • 424
9 votes
Accepted

How does an unsupervised learning model learn?

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 ...
Matthew Gray's user avatar
  • 4,262
9 votes
Accepted

What are the differences between an agent and a model?

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 ...
nbro's user avatar
  • 40.5k
8 votes

What is the relevance of AIXI on current artificial intelligence research?

"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 ...
Matthew Gray's user avatar
  • 4,262
8 votes
Accepted

What is the difference between parametric and non-parametric models?

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 ...
Saurav Maheshkar's user avatar
6 votes

What is the relevance of AIXI on current artificial intelligence research?

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 ...
nbro's user avatar
  • 40.5k
6 votes

What causes a model to require a low learning rate?

Gradient Descent is a method to find the optimum parameter of the hypothesis or minimize the cost function. where alpha is learning rate If the learning rate is high then it can overshoot the ...
Posi2's user avatar
  • 358
6 votes

After a model has been trained, how do I use it to address the real-world problems?

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 ...
Neil Slater's user avatar
6 votes
Accepted

What is the "thing" which is trained in AI model training

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,...
Neil Slater's user avatar
6 votes

How to embed/deploy an arbitrary machine learning model on microcontrollers?

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 ...
John Doucette's user avatar
6 votes

What are the differences between an agent and a model?

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. ...
Cohensius's user avatar
  • 413
5 votes

Rollout algorithm like Monte Carlo search suggest model based reinforcement learning?

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 ...
Dennis Soemers's user avatar
  • 10.3k
5 votes

Are there any computational models of mirror neurons?

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 ...
NietzscheanAI's user avatar
5 votes

What are the real world uses for SAT solvers?

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-...
Serhiy Yevtushenko's user avatar
5 votes
Accepted

What are the real world uses for SAT solvers?

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 ...
Matthew Gray's user avatar
  • 4,262
5 votes

What is the fundamental difference between an ML model and a function?

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 ...
nbro's user avatar
  • 40.5k
4 votes

What is the relevance of AIXI on current artificial intelligence research?

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 ...
NietzscheanAI's user avatar
4 votes
Accepted

How to distinguish AI modeling from implementation?

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 ...
NietzscheanAI's user avatar
4 votes

Are mathematical models sufficient to create general artificial intelligence?

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, ...
Neil Slater's user avatar
4 votes
Accepted

Is a deep technical understanding of neural networks required outside of research?

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 ...
SmallChess's user avatar
  • 1,411
4 votes

Rollout algorithm like Monte Carlo search suggest model based reinforcement learning?

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 ...
Neil Slater's user avatar
4 votes

What is the "thing" which is trained in AI model training

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 ...
Ray's user avatar
  • 346
4 votes

How to embed/deploy an arbitrary machine learning model on microcontrollers?

I found: For scikit-learn like models: MicroML, Micro-LM, Micro Learn, sklearn-porter, emlearn For deep learning models: tensorflow Lite Micro, X-CUBE-AI, Glow, NNoM Both: EdgeML, ELL These seems to ...
Hattori's user avatar
  • 201
3 votes
Accepted

How do you distinguish between a complex and a simple model in machine learning?

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 ...
Douglas Daseeco's user avatar
3 votes

State representation of position in 2D plane for Reinforcement Learning (Q Learning)

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 ...
marcotama's user avatar
  • 156
3 votes

How to distinguish AI modeling from implementation?

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 ...
Eric Platon's user avatar
  • 1,510
3 votes

Why do we need a model of the environment in Dyna?

Unlike algorithms presented in other chapters of Sutton and Barto, Dyna is a planning algorithm. That means that it makes decisions online, in a real environment, that attempt to be as optimal as ...
Neil Slater's user avatar
3 votes

Machine learning with graph as input and output

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 ...
user3551708's user avatar
3 votes

What approach should I take to model forecasting problem in machine learning?

In general, this type of problem is called a regression problem since the target variable (i.e. travel time) can take any value in a continuous domain. In theory, you can use any regression algorithms ...
Borhan Kazimipour's user avatar
3 votes
Accepted

Is there a simple way of classifying images of size differing from the input of existing image classifiers?

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 ...
Joel Joseph's user avatar

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