5 votes

What is the formal definition for manifold in artificial intelligence?

Manifold is basically a geometric object where every small region can be mapped to a euclidean space(means manifold is locally euclidean). Think of a donut, here any small region can be mapped to a ...
user avatar
4 votes
Accepted

In reinforcement learning, why are policies defined as functions of states and not observations?

Ultimately, a policy must be such that is is possible for an agent to execute it. If the policy depends on the state, the implicit assumption is that the agent has knowledge of the state and can ...
user avatar
  • 401
4 votes

When can I call an entity a hyperparameter?

In older machine learning literature the given definition of hyperparameters was explicitly the same used in Bayesian statistics, i.e. a hyperparameter is a parameter of a prior distribution For ...
user avatar
3 votes

If a policy is epsilon-greedy, is it technically stochastic?

I would argue it is just stochastic because it chooses the current best action with probability $1-\epsilon+\epsilon/|A|$ and then selects randomly among the rest of the actions with the remaining ...
user avatar
  • 809
3 votes

What is the formal definition for manifold in artificial intelligence?

The definition is the same as in Mathematics and, I suppose, elsewhere: it is a topological space such that the vicinity of each point is homeomorphic to a disk in $\mathbb{R}^n$ (note, that dimension ...
user avatar
2 votes

What makes a transformer a transformer?

It's about self-attention, a mechanism that targets parallelism among other goals (see 1706.03762.pdf - Why Self-Attention). From What Is a Transformer Model? | NVIDIA Blogs: How Transformers Got ...
user avatar
2 votes

If a policy is epsilon-greedy, is it technically stochastic?

Yes - you can think of an epsilon-greedy policy as a mixture of a policy that chooses an action at random (the stochastic part) and a possibly deterministic policy used otherwise. The value of epsilon ...
user avatar
  • 401
2 votes

What does it mean by "gradient flow" in the context of neural networks?

It has. Gradient flow or more generally flow is a well known concept in maths. Say we have a function $f:\mathbb R^n \longrightarrow \mathbb R^n$ and a function $\theta:[0,\infty)\longrightarrow \...
user avatar
2 votes

When can I call an entity a hyperparameter?

Is it okay to call anything that needs to be learned outside the training algorithm a hyperparameter? I think so, yes. Personally, I would reserve the term to discuss values that I could choose ...
user avatar
  • 24.5k
1 vote

What is meant by sub-region of an image?

It seems that they are informally using the term "sub-region" to refer to the section of the image with which you multiply the kernel to produce a scalar value of the feature map (which they ...
user avatar
  • 34.4k
1 vote

What does it mean by "gradient flow" in the context of neural networks?

Here is my idea of what that means: Gradient flow is an abstract term to describe properties of the gradient. The gradient is calculated by propagating the error backwards through the networks, ...
user avatar
  • 671
1 vote
Accepted

What exactly is data augmentation?

Data augmentation typically refers to the creation of new (training) data/instances (e.g. images) by e.g. modifying existing training/instances data in order to avoid over-fitting and improve the ...
user avatar
  • 34.4k
1 vote

What is the definition of a trace of a tensor?

The concepts of trace and tensor also appear in other contexts outside of machine learning (ML), like quantum computing, so an answer to your question may be given independently of ML, but that may ...
user avatar
  • 34.4k
1 vote

Is there any difference between the phrases "text representation" and "text feature representation"?

I think that literature is simply inconsistent in this regard. But here's a distinction that I think helps to shade a bit of light on this question: text representation: as you said we have to convert ...
user avatar
1 vote

What is the definition of "confidence interval" around a (complicated) function?

Off the top of my head, I don't know the very specific definition of confidence interval (or whether it's only defined for the parameters of a model), as I am not a statistician. In any case, ...
user avatar
  • 34.4k
1 vote

What is non-Euclidean data?

Where does this type of data arise? In terms of learning on non-Euclidean data, it was probably first coined by prof. Bronstein here. Recently, prof. Bronstein published, along with other top authors ...
user avatar
1 vote

What is non-Euclidean data?

It's hard to say because Euclidean space is defined with respect to some kind of metric, so without any clearer exposition on the nature of the data/problem, the phrase itself may or may not be clear. ...
user avatar
1 vote

Why are neural networks considered to be artificial intelligence?

AI is not only about neural networks. Formal proof assistants (like Coq, or Frama-C) are in some circles considered as AI. Projects like DECODER have an AI flavor. Symbolic AI systems (like RefPerSys) ...
user avatar

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