Artificial Intelligence Stack Exchange Community Digest

2023 Community Moderator Election

The community moderator election is currently in the election phase.

Please cast your vote by March 8!

Top new questions this week:

Reference request: AI panel discussion 2012

I have seen (probably on youtube) the recording of a panel discussion at an AI conference around 2012 (year could be wrong, but close) where the audience was polled for the question of when will AI …

reference-request

asked by Ziofil Score of 2

Can NEAT produce output which has no connection with any other node?

I recently developed a little tool called Neat Cars where you can drawa track, place a car and watch the NEAT algorithm in action (including the ANN). However, I saw something that caught my attention:…

neural-networks python neat

asked by Roux Score of 1 answered by Neil Slater Score of 1

Creating a support chat bot for my business

I am trying to create a kind of Support Bot to answer my clients about specific technical details about WordPress plugins that I sell. The goal is that the /completitions api would be feeded a prompt …

python open-ai embeddings fine-tuning

asked by digitalzoomstudio Score of 1 answered by kokumajutsu Score of 1

Can action be dominated by state features in actor-critic algorithms?

I have a case where my state consists of relatively large number of features, e.g. 50, whereas my action size is 1. I wonder whether my state features dominate the action in my critic network. I …

deep-rl actor-critic-methods soft-actor-critic td3

asked by Mika Score of 1 answered by chessprogrammer Score of 1

Can I use zero-padded input and output layers in a 1D convnet to predict an element of interest from a variable-length input sequence?

I have developed a small encoding algorithm that accepts a time series of n = 750 samples and m = 1 feature from a scientific …

neural-networks deep-learning convolutional-neural-networks

asked by Vranvs Score of 1

Question about “unsupervised learning objective” in the GPT-2 paper

I find it difficult to understand the following from the GPT-2 paper. Language modeling is also able to, in principle, learn the tasks of McCann et al. (2018) without the need for explicit …

gpt-2

asked by Tom Bennett Score of 1

Is data useless for a neural network if some inputs are derivatives of other inputs?

That is, if some of the inputs to a neural network can be calculated by a pre-determined function whose variables are other inputs, then are those specific inputs useless? For example, suppose there …

neural-networks training datasets input-layer

asked by BlueSnake Score of 1 answered by chessprogrammer Score of 2

Greatest hits from previous weeks:

What is the relation between Q-learning and policy gradients methods?

As far as I understand, Q-learning and policy gradients (PG) are the two major approaches used to solve RL problems. While Q-learning aims to predict the reward of a certain action taken in a certain …

reinforcement-learning q-learning policy-gradients comparison

asked by sloth Score of 41 answered by Neil Slater Score of 45

Why do we need explainable AI?

If the original purpose for developing AI was to help humans in some tasks and that purpose still holds, why should we care about its explainability? For example, in deep learning, as long as the …

philosophy social explainable-ai

asked by malioboro Score of 69 answered by Djib2011 Score of 75

How do I handle large images when training a CNN?

Suppose that I have 10K images of sizes $2400 \times 2400$ to train a CNN. How do I handle such large image sizes without downsampling? Here are a few more specific questions. Are there any …

neural-networks deep-learning image-recognition convolutional-neural-networks

asked by WaterRocket8236 Score of 25 answered by Maxim Score of 22

What are some well-known problems where neural networks don't do very well?

Background: It’s well-known that neural networks offer great performance across a large number of tasks, and this is largely a consequence of their universal approximation capabilities. However, in …

neural-networks deep-learning reference-request applications

asked by ABIM Score of 55 answered by Anshuman Kumar Score of 31

Why is A* optimal if the heuristic function is admissible?

A heuristic is admissible if it never overestimates the true cost to reach the goal node from $n$. If a heuristic is consistent, then the heuristic value of $n$ is never greater than the cost of its …

search proofs heuristics a-star admissible-heuristic

asked by Wizard Score of 13 answered by John Doucette Score of 13

How can Transformers handle arbitrary length input?

The transformer, introduced in the paper Attention Is All You Need, is a popular new neural network architecture that is commonly viewed as an alternative to recurrent neural networks, like LSTMs and …

natural-language-processing recurrent-neural-networks long-short-term-memory transformer

asked by chessprogrammer Score of 25 answered by tsu Score of 23

What are some examples of intelligent agents for each intelligent agent class?

There are several classes of intelligent agents, such as: simple reflex agents model-based reflex agents goal-based agents utility-based agents learning agents Each of these agents behaves slightly …

definitions intelligent-agent multi-agent-systems

asked by practronix512 Score of 8 answered by amjad khatabi Score of 9

Can you answer these questions?

Coding a conversational AI which remembers previous context

I am trying to code a proper conversational AI which remembers previous context and answers accordingly (something like a micro ChatGPT). Additionally I want the AI to work on a custom knowledge base …

natural-language-processing transformer generative-model language-model

asked by JAYDEEP GHOSE Score of 1

Representing non-fixed state-spaces in RL algorithms

How I can define the state of an environment where I don’t have a fixed representation for states? E.g. the state at one step is a list of size 5 and in another state is a list of size 6. What is the …

reinforcement-learning deep-rl

asked by Saeid Ghafouri Score of 1