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.
129
questions
-1
votes
0
answers
16
views
Why is even q estimation reduced but the agent cannot predict correctly after training? (offline q learning)
I am going to implement Algorithm 1 in this paper.
When I train the agent, it was gradually reduced the q estimate and, after training agent cannot predict correctly. What is the reason for that?
0
votes
1
answer
44
views
Difficulty in coding research papers [closed]
I understood how Yolov1 works but finding difficulty in coding it. How should I proceed?
-3
votes
1
answer
217
views
Why would an AI researcher publish their breakthrough models solely on arxiv?
My question is in general why would an AI researcher choose to publish solely on arxiv, and what are the downsides and upsides?
I understand on the one hand arxiv allows for rapid release of results. ...
-1
votes
4
answers
115
views
As a intermediate in Deep Learning, from which research paper should I start reading from? [closed]
I have done Andrew Ng's ML and DL courses, and some projects and implemented some important ML algorithms from scratch. Now reading the deep learning book. <=(Edited)
I want to start from the ...
0
votes
1
answer
51
views
How do I implement the 'gradient clipping' in the Neural Replicator Dynamics paper?
The paper is here https://arxiv.org/pdf/1906.00190.pdf
and the relevant paragraph where they explain their method is below:
It's still not clear to me how this is meant to work exactly. In the pseudo-...
0
votes
0
answers
22
views
How to find AI research papers where authors provide source codes that will reproduce the experiments described in the paper?
It is important for a research paper to include raw data and code for scientific replicability, verifiability, and falsifiability.
However, as noted by nbro, roughly 5% percent of papers have code ...
1
vote
1
answer
60
views
Is it common that an applied deep learning research paper does not disclose any raw data and source code? [duplicate]
I think it is important for a research paper to include raw data and code for scientific replicability, verifiability, and falsifiability. However, recently, most of the research paper I read does not ...
0
votes
1
answer
38
views
How can I demonstrate a novel ML classification algorithm has value?
I designed a ML classification algorithm that's simple, efficient, and effective. It's not perfect, but seems to be widely applicable across domains.
I'd like to submit it for publication, but I don't ...
0
votes
0
answers
22
views
Is there any sort of 'best practice' for giving the general public access to deep learning models to accompany academic papers?
Is there any sort of 'best practice' for giving the general public access to deep learning models to accompany academic papers?
2
votes
1
answer
131
views
Can AI be used for grading code copy exercises and adjust difficulty based on these scores?
I'm a senior in a bachelor Multimedia and Creative Technology. My experience is mostly full-stack web app development.
For my bachelor's thesis, I need to do research in a subject I have no experience ...
8
votes
3
answers
1k
views
Is it okay to use publicly available Instagram videos to train an AI?
Since I haven't found any good training data for my university project, I want to use pictures and videos from public Instagram profiles. Am I allowed to do that?
5
votes
2
answers
496
views
Should I repeat lengthy deep learning experiments to average results ? How to decide how many times to repeat?
I am doing my MSc thesis on deep learning. My model takes many hours to train. Part of what I do is trying different parameters and settings hoping that they will achieve different results. But I ...
6
votes
0
answers
83
views
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 ...
0
votes
0
answers
30
views
Non-locally Electrically Programmable Logic Gates - Technological Advances Progress
Preface: I’d like to clarify that I understand what a relay is and that a PLC uses a fairly conventional microprocessor that only digitally establishes logical logic gate configuration as a digitally ...
1
vote
1
answer
198
views
Why many deep learning research papers continue to be in arXiv?
There are plenty of research papers, especially in deep learning are present only in arXiv with large number of citations. I cannot find them in journals as peer-reviewed ones.
For example if I search ...
2
votes
1
answer
111
views
Do researchers generally treat tensors just as mathematical objects with certain shape?
Most of the practical research in AI that includes neural networks deals with higher dimensional tensors. It is easy to imagine tensors up to three dimensions.
When I ask the question How do ...
0
votes
0
answers
34
views
Do deep learning researchers generally visualize intermediate steps?
Many researchers in deep learning research come up with new CNN architectures.
The architectures are (just) combinations of a few existing layers.
Along with their mathematical intuition, in general, ...
2
votes
0
answers
43
views
How much research, approximately, is done in ANNs?
Does someone know where can I find information about how much research, nowadays, is done in ANNs?
I've checked in this document Redes Neuronales: Conceptos básicos y aplicaciones, Universidad ...
4
votes
2
answers
318
views
What algorithms are used in Artificial General Intelligence research?
I've read on wiki that already in 2017 there were over 40 institutions researching AGI, and I wonder what type of algorithms are being studied and developed in this field.
For example, for comparison ...
1
vote
0
answers
88
views
Which topics about/in OpenCog could be researched in a Ph.D. thesis
In this interview with Lex Fridman and Ben Goertzel, at 2:23:48, Lex asks about possibilities for young people in the domain of AGI research. Ben Goertzel then answers that there are various ...
5
votes
1
answer
64
views
In the field of Deep Learning research, what considerations do researchers take into account when inventing new neural network models?
I am not a researcher, but I am curious to know what considerations are relevant to take into account during research for the invention of a new neural network model, and what relevant knowledge ...
0
votes
1
answer
81
views
On what basis is MATLAB "inflexible" to perform ML/AI research on it?
During a course review, I have provided my opinion on the course overall. I stated that MATLAB is also a great environment to program and do research for ML/AI, but my professor seemed to have taken ...
2
votes
0
answers
112
views
Did the Hutter Prize help research in artificial intelligence in any way?
Wikipedia states:
The Hutter Prize is a cash prize funded by Marcus Hutter which rewards data compression improvements on a specific 1 GB English text file.
The goal of the Hutter Prize is to ...
4
votes
1
answer
68
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?
1
vote
0
answers
31
views
Is the framework provided by this paper for checking the constraints of AI systems really new?
The authors of this paper present a framework for checking the constraints of AI systems using formal argumentative logic between 2 agents: an interrogating agent and a suspect agent. The ...
3
votes
0
answers
77
views
What is the reverse of passing a Turing test by a human pretending to be a robot that can't be identified?
A Turing Test is a method of inquiry for determining whether or not a computer is capable of thinking like a human being. In an ideal Turing test, it would be clear to differentiate between a real ...
3
votes
1
answer
284
views
Are there any active areas of research in machine learning that do not involve neural networks at all?
So far, I have not been able to find many papers that do not involve neural networks, so I was hoping I can gain some insight here. Any references would be greatly appreciated.
2
votes
1
answer
110
views
Can TensorFlow, PyTorch, and other mainstream ML frameworks be used for research-grade work in AI?
Many authors of research papers in AI (e.g. arXiv) write their neural networks from the ground-up, using low-level languages like C++ to implement their theories. Can existing open source frameworks ...
5
votes
1
answer
141
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 ...
0
votes
1
answer
32
views
What is the process of inventing deep neural network models? How researchers deal with long training times?
After reading this topic on GitHub how long time it takes to train YOLOV3 on coco dataset I was wondering how researchers deal with long training times while inventing new architectures.
I imagine ...
1
vote
0
answers
100
views
Can any area of math come into play in Machine Learning Research?
As I read online following areas in mathematics come into play in ML research
Linear Algebra
Calculus
Differential Equations
Probability
Statistics
Discrete Mathematics
Optimization
Analytic Geometry
...
3
votes
1
answer
181
views
How do AI researchers imagine higher dimensions?
We can visualize single, two, and three dimensions using websites or imagination.
In the context of AI and, in particular, machine learning, AI researchers often have to deal with multi-dimensional ...
4
votes
2
answers
330
views
How much is currently invested in artificial general intelligence research and development?
How much is currently invested in artificial general intelligence research and development worldwide?
Feel free to add company or VC names, but this is not the point. The point is to get an idea of ...
1
vote
0
answers
100
views
How differentiable programming and programming language supporting it will potentially help the development towards AGI?
After the state of the art Deep Learning techniques/algorithms being implemented in low-level languages like Objective-C, C++, etc to high-level languages like Python, JS, etc. and with the help of ...
3
votes
1
answer
106
views
Research paths/areas for improving the performance of CNNs when faced with limited data
I've been reading through the research literature for image processing, computer vision, and convolutional neural networks. For image classification and object recognition, I know that convolutional ...
1
vote
1
answer
73
views
As an AI researcher, what subjects do you find yourself referring to most often? [closed]
This is a bit of a weird question.
I am hoping to create an online reference since I have some downtime. I know some about statistics but very little about computer science. As a result, the ...
0
votes
1
answer
144
views
What are the mathematical prerequisites needed to understand research papers on neural networks? [closed]
I know we have developed some mathematical tools to understand deep neural networks, gradient descent for optimization, and basic calculus. Recently, I encountered arxiv paper that describes higher ...
0
votes
0
answers
41
views
Is it a good idea to train a neural network to classify images without base-hypothesis?
I'm a relative beginner in deep learning (understand by that, I'm doing my first Kaggle competition right now, and I have loads to learn still) and I was just wondering something.
Let's say you have ...
2
votes
0
answers
363
views
Ways to keep up with the latest developments in Machine Learning and AI?
With over 100 papers published in the area of artificial intelligence, machine learning and their subfields every day (source), accounting for ~3% of all publications world wide per year (source) and ...
3
votes
4
answers
311
views
How can I read any AI paper?
I have studied linear algebra, probability, and calculus twice. But I don't understand how can I reach the level that I can read any AI paper and understand mathematical notation in it.
What is your ...
1
vote
0
answers
200
views
Creating 4k HDR video from 720p footage
So, my company recently bought a big 4k HDR TV for our reception, where we keep showing some videos that were originally shot/created at 720p resolution. Before this, we had a relatively small HD TV, ...
1
vote
1
answer
83
views
What are the real applications of hierarchical temporal memory?
What are the real applications of hierarchical temporal memory (HTM) in machine learning (ML) these days?
1
vote
1
answer
128
views
Are there any conferences dedicated to artificial general intelligence?
Similarly to What are the scientific journals dedicated to artificial general intelligence?, are there any conferences dedicated to artificial general intelligence?
3
votes
1
answer
1k
views
How does publishing in the deep learning world work, with respect to journals and arXiv?
Let's say I implemented a new deep learning model that pushed some SOTA a little bit further, and I wrote a new paper about for publication.
How does it work now? I pictured three options:
Submit it ...
24
votes
3
answers
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 ...
1
vote
0
answers
52
views
What are the procedures to get RL paper results? [closed]
I finished working on a new algorithm in Reinforcement Learning, I need to compare it to some well-known algorithms. That's why I need to know the step-by-step procedures that RL researchers usually ...
1
vote
1
answer
90
views
What are some conferences for publishing papers on graph convolutional networks?
What are some conferences for publishing papers on graph convolutional networks?
1
vote
0
answers
26
views
Has there been any work done on AI-driven operant conditioning?
For example, a RL algorithm that gains points when a rat presses a lever and loses points when it dispenses a pellet, water, treat, and/or sugar water. After a few days of controlling the rewards ...
3
votes
2
answers
198
views
What are the scientific journals dedicated to artificial general intelligence?
Apart from Journal of Artificial General Intelligence (a peer-reviewed open-access academic journal, owned by the Artificial General Intelligence Society (AGIS)), are there any other journals (or ...
1
vote
1
answer
46
views
Is the paper "Reducing the Dimensionality of Data with Neural Networks" by Hinton relevant?
Is the paper "Reducing the Dimensionality of Data with Neural Networks" by G. Hinton and R. Salakhutdinov relevant?
It seems that the deep learning textbook by Goodfellow, Bengio & Courville (...