Questions tagged [reference-request]
Use when requesting examples of research or research papers, books, articles, blog posts or courses. For example, "Is there any published research about X?" or "What are good examples of Y in research?".
504 questions
4
votes
1
answer
146
views
What are the current state-of-the-art techniques for reducing hallucinations in large language models?
I’m studying how modern large language models (LLMs) generate factual and verifiable outputs. Despite improvements in training data quality and model alignment, hallucinations still occur.
My question ...
- 637
1
vote
1
answer
103
views
What are some good textbooks or publications on swarm and or emergent intelligence?
I'm looking at studying swarm intelligence and complex systems a bit as a side project or potential precursor to a graduate program and am looking for text recommendations (I double-majored in ...
- 181
3
votes
4
answers
306
views
Which books are there on AI in medical practice?
I'm a kind of new to AI. I'm a neurologist.
I'm looking for a book on AI, which covers topics of traditional AI, classical ML, deep learning, supervised learning, unsupervised learning, reinforcement ...
- 145
4
votes
1
answer
110
views
How is AI presently being applied in the health sector and should patients be afraid of AI making decisions rather than doctors?
The usage of AI is often talked about in the healthcare industry; however, it is often ambiguous as to what that entails in practical applications.
What type of AI systems are currently being used ...
- 71
2
votes
0
answers
82
views
What are some good references for multi-developer source code assembly?
I am working on a project that explores how artificial intelligence can automatically assemble and merge software modules developed by multiple developers, while ensuring compliance with a unified ...
1
vote
1
answer
67
views
Is there a general framework for recasting optimization as an RL problem?
Recently, I read a paper about optimizing airfoil geometry using reinforcement learning. For simplicity, let's say that we want the airfoil to have a high coefficient of lift. What the paper does is ...
- 113
0
votes
1
answer
108
views
What percentages of power consumption is expected to be used by matrix multiplication in OpenAI’s data center?
The article states OpenAI would require 30million GPUs for a data center consuming 250GW.
What is the matrix multiplication portion for this power requirement?
Edit:
I am looking for percentages of ...
- 133
0
votes
0
answers
36
views
Could you suggest literature or conceptual approaches for fusing any two arbitrary input representations in DRL?
I am working on a university project exploring Contextual Reinforcement Learning (CRL) using Actor-Critic algorithms (like PPO and SAC). My focus is on how to effectively integrate the state ...
0
votes
1
answer
143
views
Good references to explain why neural networks are able to produce such realistic images
I was looking to find some good current references: articles, books, videos, etc., that explain the ability of current generation of generative models to produce very realistic images and photographs.
...
- 229
0
votes
1
answer
83
views
Are there complete, open-access resources on the wide array of activation functions in use to date?
I am in search an open access resource that covers a great deal of the activation functions that are being used in modern neural network architectures, including their use-cases, advantages, and ...
- 1,791
0
votes
0
answers
30
views
What are the biological mechanisms for learning?
Current conventional deep learning is loosely based on biology, with weighted inputs and threshold firing/activation, e.g. $\mathsf{ReLU}(Ax+b)$. The training process updates weights via SGD and ...
- 101
2
votes
1
answer
242
views
Are there any research papers with guidelines or tricks on how to use LLMs effectively?
There are several prompting techniques that can significantly enhance the performance of LLMs across a wide range of tasks, including programming.
For example, a complex problem can be recursively ...
- 131
0
votes
0
answers
88
views
"I" and the symbol grounding problem?
To those who believe symbol grounding can be solved by grounding in sensory data. How would they ground the word "I"? "I" is different. It doesn’t refer to a sensory object but to ...
- 111
1
vote
1
answer
77
views
Who argued that we're entering a 4th era of science with machine learning?
I remember reading a reference to a recent paper that argued that science today is in its 4th stage (paradigm?), the era of modelling with machine learning. The 3rd was that of Newton, Kepler, et al.
...
- 599
1
vote
1
answer
169
views
What are the leading methods to estimate Epistemic Uncertainty in Large Language Models?
Epistemic uncertainty is uncertainty that arises from a lack of knowledge, for instance in machine learning epistemic uncertainty can be caused by a lack of training data. Estimating epistemic ...
- 1,359