# Tag Info

### Is plain autoencoder a generative model?

An autoencoder is not considered a generative model, because it only reconstructs the given input. You could use the decoder like a generative model by putting in different vectors. However, the ...
• 356
Accepted

### How do I create an AI controller for Pacman?

About the environments For the controller part of your question, I would advice looking at openAI gym. https://www.gymlibrary.ml/content/environment_creation/ #how to make your own gym enviroment ...
• 349
Accepted

### How to tackle the human error made in labeling datasets for classification tasks like facial expression recognition?

In general the only way to deal with this is by quantifying these labeling mistakes in the output of the model, since the model will learn for them. And in many cases these are not really mistakes, ...
• 566
Accepted

### Why do we train the discriminators k times but train the generator only 1 time in a iteration in GAN?

The answer to your question can be found in [1, sec. 4.4]. Briefly, the GAN optimization problem is a mini-max game, and early on the proposition of GANs, the authors had the idea that one should ...

### 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 ...
1 vote

### What are the possible ways to handle imbalance in multi-class image datasets?

Yes this is certainly possible... What you want to do is apply a weight to particular classes by proportion of the imbalance(assuming nothing else related to the problem is of note). See this post for ...
• 1,155
1 vote
Accepted

### How does the hidden activation differ from the output, at any time step for a SimpleRNN?

They are not the same always, the activation (as you called it) here is the hidden state (I think it's a in your slide), now you can have the output is the same as ...
• 361
1 vote
Accepted

### Where does the "rectified" in ReLU come from?

I think it is by analogy with an electrical rectifier. A rectifier allows current to flow in one direction but blocks current in the other direction. Or if you prefer it allows voltage in one polarity ...
• 452
1 vote
Accepted

### Does LSTM provide any unique value or advantages compared to other algorithms, including "vanilla" RNN?

LSTMs were the state-of-the-art (SOTA) in many cases (e.g. machine translation) until transformers came along - now I don't really know the SOTA or where LSTMs still perform better than e.g. ...
• 33.8k
1 vote

### Using GraphSAGE model for multigraph datasets

My question is if GraphSAGE is suitable for this kind of data? To my knowledge, GraphSAGE is designed for very large graphs with highly connected nodes (like social networks). The neighborhood ...
• 356
1 vote

### How to properly name given type of classification problem?

I think what you are looking for is multi-label classification. Multi-label classification can take care of both of your constraints - each data sample can be classified according to two different ...
1 vote

### What do we mean by the notation $\mathbf{x}_{p} \in \mathbb{R}^{N \times\left(P^{2} \cdot C\right)}$?

This itself isn't really an expression but a description of what $x_p$ looks like. Specifically, $x_p$ is a real-valued vector with the shape [N, P^2 * C]. Of ...
• 356
1 vote

### Why are embeddings added, not concatenated?

First of all, I think it is very hard to properly reason about these things, but there are a few points that might justify using sum instead of concatenation. For example, concatenation would have the ...
• 356
1 vote

### Is the described Q-table considered large?

There a couple of "rules of thumb" you might apply to decide whether a Q table is large enough that some kind of approximation would help: Does it fit into memory? Does the rate of ...
• 23.9k
1 vote
Accepted

### How to compare memory requirements for tabular Q-learning vs deep neural network?

You don't say, but I suspect from your description, that you have designed the neural network to operate over one-hot-encoding representations of states and actions. Using such a representation offers ...
• 23.9k
1 vote

### How to use a trained neural network to find optimal function inputs?

You can try to optimize the 4 input parameters to maximize or minimize the output of the neural network with a mathematical optimizer. The scipy.optimize package has some methods you can use. It is ...
• 111

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