Questions tagged [research]

For questions related to in-depth study or academic research. Do NOT use this tag when you are trying to find something out.

Filter by
Sorted by
Tagged with
48
votes
4answers
75k views

How to select number of hidden layers and number of memory cells in an LSTM?

I am trying to find some existing research on how to select the number of hidden layers and the size of these of an LSTM-based RNN. Is there an article where this problem is being investigated, i.e., ...
32
votes
3answers
23k views

Why is Lisp such a good language for AI?

I've heard before from computer scientists and from researchers in the area of AI that that Lisp is a good language for research and development in artificial intelligence. Does this still apply, with ...
21
votes
3answers
4k views

Why do most deep learning papers not include an implementation?

I'm a novice researcher, and as I started to read papers in the area of deep learning I noticed that the implementation is normally not added and is needed to be searched elsewhere, and my question is ...
17
votes
2answers
318 views

What research has been done in the domain of “Identifying sarcasm in text”?

Identifying sarcasm is considered as one of the most difficult open-ended problems in the domain of ML and NLP. So, was there any considerable research done in that front? If yes, then what is the ...
14
votes
1answer
517 views

How to stay a up-to-date researcher in ML/RL community?

As a student who wants to work on machine learning, I would like to know how it is possible to start my studies and how to follow it to stay up-to-date. For example, I am willing to work on RL and MAB ...
13
votes
4answers
2k views

How close are we to creating Ex Machina?

Are there any research teams that attempted to create or have already created an AI robot that can be as close to intelligent as these found in Ex Machina or I, Robot movies? I'm not talking about ...
13
votes
3answers
2k views

What sort of mathematical problems are there in AI that people are working on?

I recently got a 18-month postdoc position in a math department. It's a position with relative light teaching duty and a lot of freedom about what type of research that I want to do. Previously I was ...
13
votes
3answers
1k views

What are some implications of Gödel's theorems on AI research?

Note: My experience with Gödel's theorem is quite limited: I have read Gödel Escher Bach; skimmed the 1st half of Introduction to Godel's Theorem (by Peter Smith); and some random stuff here and there ...
12
votes
3answers
2k views

Why spend so much time and money to build AIs to play games?

I was reading about John McCarthy and his orthodox vision of Artificial Intelligence. To me, it seems like he was not very much in favour of resources (like time and money) being used to make AIs play ...
11
votes
1answer
4k views

When did Artificial Intelligence research first start?

When did research into Artificial Intelligence first begin? Was it called Artificial Intelligence then or was there another name?
11
votes
1answer
305 views

What are the state-of-the-art results on the generalization ability of deep learning methods?

I've read a few classic papers on different architectures of deep CNNs used to solve varied image-related problems. I'm aware there's some paradox in how deep networks generalize well despite ...
11
votes
1answer
188 views

Strategic planning and multi dimensional knapsack problem

I'm trying to find a planning approach to solve a problem that attempts to model learning of new material. We assume that we only have one resource such as Wikipedia, which contains a list of articles ...
10
votes
4answers
2k views

What is the most sophisticated AI ever made?

What is the most advanced AI software/system that humans have made to date, and what does it do?
10
votes
3answers
563 views

Are there any textual CAPTCHA challenges which can fool AI, but not human?

Are there any modern techniques of generating textual CAPTCHA (so person needs to type the right text) challenges which can easily fool AI with some visual obfuscation methods, but at the same time ...
10
votes
2answers
889 views

How much of Deep Mind's work is actually reproducible?

Deep Mind has published a lot of works on deep learning in the last years, most of them state-of-the-art on their respective tasks. But how much of this work has actually been reproduced by the AI ...
9
votes
4answers
2k views

What are the top artificial intelligence journals? [closed]

What are the top artificial intelligence journals? I am looking for general artificial intelligence research, not necessarily machine learning.
9
votes
3answers
4k views

What are the mathematical prerequisites to be able to study artificial general intelligence?

What are the mathematical prerequisites to be able to study artificial general intelligence (AGI) or strong AI?
8
votes
2answers
1k views

How can people contribute to AGI research?

Is there a way for people outside of the core research community of AGI to contribute to the cause? There are a lot of people interested in supporting the field, but there is no clear way to do that. ...
8
votes
2answers
159 views

How can AI researchers avoid “overfitting” to commonly-used benchmarks as a community?

In fields such as Machine Learning, we typically (somewhat informally) say that we are overfitting if improve our performance on a training set at the cost of reduced performance on a test set / the ...
8
votes
1answer
333 views

What are some resources on continuous state and action spaces MDPs for reinforcement learning?

Most introductions to the field of MDPs and Reinforcement learning focus exclusively on domains where space and action variables are integers (and finite). This way we are introduced quickly to Value ...
8
votes
1answer
492 views

What is an intuitive explanation of how Google's AutoML works?

I recently read that Google has developed a new AI that anyone can upload data to and it will instantly generate models i.e. an image recognition model based off that data. Can someone explain to me ...
8
votes
1answer
218 views

What are the most recent and influential breakthroughs in NLP?

I'm looking at the history of NLP, starting in the 1950s, with the Georgetown–IBM experiment. What are examples of the most recent (e.g. in the last 5-10 years) and influential breakthroughs in ...
7
votes
2answers
822 views

Is anybody still researching GOFAI?

A lot of textbooks and introductory lectures typically split AI into connectionism and GOFAI (Good Old Fashioned AI). From a purely technical perspective, it seems that connectionism has grown into ...
7
votes
2answers
752 views

Where to publish a first article in Deep Reinforcement Learning?

What would be examples of journals that are good for a first publication in the field of Deep Reinforcement Learning? I am in the process of writing about the research results of DQN-related ...
7
votes
1answer
181 views

How good is AI at generating new, unseen [visual] examples?

By new, unseen examples; I mean like the animals in No Man's Sky. A couple of images of the animals are: So, upon playing this game, I was curious about how good is AI at generating visual ...
6
votes
3answers
975 views

Perfect play in information incomplete games

As titled, is there such thing as perfect play (or at least "perfectly optimal") in a game with incomplete information? Or at least a proof as to show why there cannot? Naively (and seemingly ...
5
votes
1answer
266 views

Is the neuron adequately comprehended?

It is possible that the signal handling of a neuron is outside the engineering comprehension of the most astute of human brains, even after the relationships of inputs to outputs are statistically ...
5
votes
1answer
180 views

Did the Facebook robots both want everything but the balls?

According to this article, two Facebook ai's had the following "creepy" negotiation over a transaction: Bob: i can i i everything else . . . . . . . . . . . . . . Alice: balls have zero to ...
5
votes
2answers
76 views

Where to publish replications of machine learning papers? [closed]

If I replicated the results of a machine learning paper, is there a website that I can publish my code to that collects informal replication attempts? https://paperswithcode.com/ allows anyone to ...
5
votes
2answers
437 views

Neural network for data visualization

At my work we're currently doing some research into data visualisation for highly inter connected data, basically graphs. We've been implementing all sorts of different layouts and trying to see ...
5
votes
1answer
216 views

Self-driving control logic based on semantic segmentation

In the context of autonomous driving, two main stages are typically implemented: an image processing stage and a control stage. The first aims at extracting useful information from the acquired image ...
5
votes
2answers
1k views

What is the current state-of-the-art in Reinforcement Learning regarding data efficiency?

In other words, which existing reinforcement method learns in fewest episodes? R-Max comes to mind, but its very old and I'd like to know if there is something better now.
5
votes
3answers
430 views

What are the likely AI advancements in the next 10 years? [closed]

What are the likely AI advancements in the next 5-10 years? I first want to specify that I have nearly no knowledge about How AI works. I just have interest to know more and more about it. Some ...
4
votes
4answers
339 views

Is private research with low funds still feasible in the field of AI?

My question assumes that a private researcher doesn't have access to anything stronger than a modern PC with a high end GPU to implement his projects. He can also use cloud computing but with limited ...
4
votes
1answer
864 views

What does “death” intuitively mean in the paper “Death and Suicide in Universal Artificial Intelligence”?

In the paper Death and Suicide in Universal Artificial Intelligence, a proposal is given for what death could mean for Artificial Intelligence. What does this mean using English only? I understand ...
4
votes
2answers
238 views

How can you do AI research by your own?

Let's say you want to do AI research and publish some papers just by your own. Would you send them to an AI journal using just your name? Which AI journals are recommended?
4
votes
1answer
155 views

Is there a reason to use TensorFlow over PyTorch for research purposes?

I've been using PyTorch to do research for a while and it seems to be quite easy to implement new things with. Also, it is easy to learn and I didn't have any problem with following other researchers ...
4
votes
2answers
236 views

Are Neural Net architectures accidental discoveries?

Recently, I have been learning about new neural networks, which are used for specialised purposes, like speech recognition, image recognition, etc. The more I discover the more I get amazed by the ...
4
votes
2answers
748 views

Can neural networks be better than human experts at prediction of greyhound racing results?

Were there any studies which checked the accuracy of neural network predictions of greyhound racing results, compared to a human expert? Would it achieve a better payoff?
4
votes
4answers
677 views

Diagnosing mental health problems using Artificial Intelligence / Machine Learning techniques

I've seen events, like CogX and articles which describe how machine learning techniques or algorithms can be used to diagnose mental health issues. Here is my question; How can artificial ...
4
votes
1answer
227 views

Berkeley AI Course Question on Nearly Zero Sum Games

I am drawing this question from Berkeley's AI course (also not sure if it is the correct place to ask, so I apologize ahead of time) https://inst.eecs.berkeley.edu/~cs188/pacman/course_schedule.html ...
4
votes
1answer
339 views

How would we know if AI development will continue to be multipolar, or will become monolithic?

Currently, many different organizations do cutting-edge AI research, and some innovations are shared freely (at a time lag) while others are kept private. I'm referring to this state of affairs as '...
4
votes
1answer
55 views

Is there a document with a list of conjectures or research problems regarding reinforcement learning (like the Millennium Prize Problems)?

Is there a document with a list of conjectures or research problems regarding reinforcement learning like the Millennium Prize Problems?
4
votes
1answer
92 views

Is there any research on the identification of a person's feelings using features such as facial expressions or body temperature?

People could be sad, happy, depressive, angry, nervous, calm, relaxed, bored, etc. I don't know how to express all of these feelings and emotions in English terms (I'm not an English native speaker), ...
4
votes
3answers
418 views

Does it exist a human-like artificial intelligence?

Does it exist a human-like artificial intelligence? I define human-like as something that can act like a human in most aspects.
4
votes
1answer
121 views

Are there any anthropological studies involving AI right now?

Are there currently any studies to simulate gradual (or sudden) implementation of AIs in the general work force?
4
votes
1answer
196 views

What can be done to correct for sampling bias introduced from (noisy) training data while training a DNN?

The obvious solution is to ensure that the training data is balanced - but in my particular case that is impossible. What corrections can one perform in such a scenario? I know that my training data ...
4
votes
1answer
80 views

Are most things generally discovered because they work empirically and later justified mathematically, or vice-versa?

In the original GloVe paper, the authors discuss group theory when coming up with equation (4). Is it possible that the authors came up with this model, figured out it was good, and then later found ...
4
votes
1answer
108 views

Research into social behavior in Prisoner's Dilemma

I've been working on research into reproducing social behavior using multi-agent reinforcement learning. My focus has been on a GridWorld-style game, but I was thinking that maybe a simpler Prisoner's ...
4
votes
0answers
156 views

Multi Agent Sokoban Search Solvers state of the art

I also asked this question here but I'm repeating it on this SE because I feel it is more relevant. No intention to spam. I am researching into coding a solver for a variant of the Sokoban game with ...