Most Popular
1500 questions
10
votes
3 answers
Why are LLMs able to reproduce bodies of known text exactly?
Mathematically, I wouldn't expect LLMs to be able to reproduce source texts exactly unless the source text was the probable outcome given some prompt. However, I have now tested HuggingFaceH4/zephyr-7b-beta, TheBloke/Llama-2-7B-Chat-GGUF, and…
Grant Curell
- 203
- 1
- 8
10
votes
2 answers
How to design a neural network when the number of inputs is variable?
I'm looking to design a neural network that can predict which runner wins in a sports game, where the number of runners varies between 2-10. In each case, specific data about the individual runners (for example, the weight, height, average speed in…
Nickpick
- 211
- 1
- 8
10
votes
3 answers
What is the difference between encoders and auto-encoders?
How are the layers in a encoder connected across the network for normal encoders and auto-encoders? In general, what is the difference between encoders and auto-encoders?
m2rik
- 333
- 1
- 9
10
votes
1 answer
Why use ReLU over Leaky ReLU?
From my understanding a leaky ReLU attempts to address issues of vanishing gradients and nonzero-centeredness by keeping neurons that fire with a negative value alive.
With just this info to go off of, it would seem that the leaky ReLU is just an…
John Brown
- 103
- 5
10
votes
4 answers
How do I select the relevant features of the data?
Recently I was working on a problem to do some cost analysis of my expenditure for some particular resource.
I usually make some manual decisions from the analysis and plan accordingly.
I have a big data set in excel format and with hundreds of…
Karan Chopra
- 291
- 1
- 8
10
votes
1 answer
A deep learning algorithm to optimize the outcome
I'm am quite new to deep learning but I think I found just the right real-world situation to start using it. The problem is that I have only used such algorithms to predict outcomes. For my new project, I need information to feed a machine with to…
Frank Malenfant
- 131
- 6
10
votes
3 answers
What do you call a machine learning system that keeps on learning?
As I understand it from this video lecture, there are three types of deep learning:
Supervised
Unsupervised
Reinforcement
All these can serve to train a neural network either only prior to its deployment or during its operating.
For the latter…
ZakC
- 347
- 2
- 7
10
votes
2 answers
Are GPT-3.5 series models based on GPT-3?
In the official blog post about ChatGPT from OpenAI, there is this paragraph explaining how ChatGPT model was trained:
We trained this model using Reinforcement Learning from Human Feedback
(RLHF), using the same methods as InstructGPT, but with…
iMad
- 203
- 2
- 5
10
votes
1 answer
How can an ensemble be more accurate than the best base classifier in that ensemble?
BACKGROUND: Ensemble classifiers are said to reduce bias by taking an "average" of predictions of several base classifiers that comprise the ensemble. However, I am uncertain if this necessarily means that they can increase accuracy. My intuition…
Snehal Patel
- 942
- 1
- 3
- 26
10
votes
2 answers
How can I encode angle data to train neural networks?
I am training a neural network where the target data is a vector of angles in radians (between $0$ and $2\pi$).
I am looking for study material on how to encode this data.
Can you supply me with a book or research paper that covers this topic…
user366312
- 311
- 1
- 12
10
votes
2 answers
Using AI to extend an imagine pattern
I have created some nice patterns using the MidJourney tool. I'd like to find a way to extend these patterns, and I was thinking about an AI tool that takes one of these patterns and extends it in all directions surrounding the original…
Nicola Lepetit
- 203
- 2
- 8
10
votes
1 answer
Is analogy necessary to artificial general intelligence?
Analogies are quite powerful in communication. They allow explaining complex concepts to people with no domain knowledge, just by mapping to a known domain. Hofstadter says they matter, whereas Dijkstra says they are dangerous. Anyway, analogies can…
Eric Platon
- 1,510
- 10
- 22
10
votes
2 answers
Is Lisp still worth learning today in the particular context of Machine learning?
Lisp was originally created as a practical mathematical notation for computer programs, influenced by the notation of Alonzo Church's lambda calculus. It quickly became the favored programming language for artificial intelligence (AI) research,…
Maheshwar Ligade
- 826
- 10
- 21
10
votes
2 answers
Is there a venue to publish negative results in AI/ML domain?
Negative results occur frequently in AI/ML research (and perhaps in other domains too). Most of the time, these results are not published. This is mostly because your typical AI/ML conference doesn't accept such papers.
However, are there any venues…
SpiderRico
- 990
- 9
- 18
10
votes
1 answer
Has anyone attempted to train an AI to learn all languages?
It seems that most projects attempt to teach the AI to learn individual, specific languages.
It occurs to me that there are relations in written and spoken words and phrases across languages - most of use have a much easier time learning more…
mindplay.dk
- 209
- 1
- 4