Skip to main content
Share Your Experience: Take the 2024 Developer Survey

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?".

156 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
8 votes
2 answers
876 views

Are there transformer-based architectures that can produce fixed-length vector encodings given arbitrary-length text documents?

BERT encodes a piece of text such that each token (usually words) in the input text map to a vector in the encoding of the text. However, this makes the length of the encoding vary as a function of ...
HelloGoodbye's user avatar
4 votes
0 answers
258 views

Why are most commonly used activation functions continuous?

I have come to notice that the most commonly used activation functions are continuous. Is there any specific reason behind this? Results such as this paper have worked on training networks with ...
ABIM's user avatar
  • 565
4 votes
2 answers
268 views

How do you measure multi-label classification accuracy?

Multi-label assignment is the task in machine learning to assign to each input value a set of categories from a fixed vocabulary where the categories need not be statistically independent, so ...
Nick's user avatar
  • 251
4 votes
0 answers
368 views

Is there a way to do reinforcement learning in POMDP?

Are there any algorithms to use reinforcement learning to learn optimal policies in partially observable Markov decision process (POMDP) i.e. when the state is not perfectly observed? More ...
Deepanshu Vasal's user avatar
4 votes
0 answers
68 views

What is the cognitive architecture with the highest IIT measure?

What contemporary information system or cognitive architecture is the one with the highest measure of the Integrated Information Theory (IIT) (that is, a theory of consciousness, which states that a ...
TomR's user avatar
  • 863
4 votes
0 answers
55 views

What are some neural network models that can use auxiliary info during training for image segmentation?

What are some deep learning models that can use supplementary information other than RGB channels for image segmentation? For example, imagine a poorly shot image of a river (blue) that shows a gap, ...
Nanako Honda's user avatar
4 votes
0 answers
75 views

What research has been done on learning non-Markovian reward functions?

Recently, some work has been done planning and learning in Non-Markovian Decision Processes, that is, decision-making with temporally extended rewards. In these settings, a particular reward is ...
Gavin Rens's user avatar
4 votes
0 answers
676 views

Is there any way and any reason why one would introduce a sparsity constraint on a deep auto-encoder?

Is there any way and any reason why one would introduce a sparsity constraint on a deep autoencoder? In particular, in deep autoencoders, the first layer often has more units than the dimensionality ...
MattSt's user avatar
  • 597
4 votes
0 answers
362 views

What are some interesting recent papers that synthesize symbolic AI with Deep Learning?

A lot of people seem to be under the impression that combining GOFAI and contemporary AI will make models more general. I'm particularly interested in reasoning through analogy or case-based reasoning....
Daniel's user avatar
  • 326
4 votes
0 answers
917 views

Can neural networks be used to study (elementary) number theoretic problems?

Can neural networks be used to study (elementary) number theoretic problems? What are examples where this has been done in the past? Or is there on the contrary an understanding that neural networks ...
Stefan Witzel's user avatar
3 votes
0 answers
43 views

What is the current state of AI regarding features of Moravec's paradox, such as sensorimotor & perception skills?

Moravec's paradox is the observation in artificial intelligence and robotics that, contrary to traditional assumptions, reasoning requires very little computation, but sensorimotor and perception ...
Qwokker's user avatar
  • 131
3 votes
0 answers
247 views

Let's Verify Step by Step: Old wine in new bottles?

In their paper "Let's Verify Step by Step" OpenAI proudly presents a new way of reward learning which shall foster LLMs' capabilities of mathematical and logical reasoning: We've trained a ...
Hans-Peter Stricker's user avatar
3 votes
2 answers
259 views

Is there any variant of perceptron convergence algorithm that ensures uniqueness?

The perceptron convergence algorithm given below ensures the convergence of weights of the perceptron provided enough data points and iterations. Although it ensures convergence by finally getting a ...
hanugm's user avatar
  • 3,890
3 votes
0 answers
524 views

Are there heuristics that play Klondike Solitaire well?

Are there heuristics that play Klondike Solitaire well? I know there are some good exhaustive search solvers for Klondike Solitaire. The best one that I know of is Solvitaire (2019) which uses DFS, (...
Cohensius's user avatar
  • 413
3 votes
0 answers
72 views

How efficient is SCAWI weight initialization method?

I'm currently in the middle of a project (for my thesis) constructing a deep neural network. Since I'm still in the research part, I'm trying to find various ways and techniques to initialize weights. ...
ChrisP's user avatar
  • 41
3 votes
0 answers
118 views

Is there a good book or paper on word embeddings?

Is there a good and modern book that focuses on word embeddings and their applications? It would also be ok to provide the name of a paper that provides a good overview of word embeddings.
ddaedalus's user avatar
  • 919
3 votes
0 answers
234 views

What are examples of good reference books on unsupervised learning?

I am looking for good introductory and advanced books on unsupervised learning. I have already read books like Probabilistic Graphical Models from D. Kholler and Pattern Recognition and Machine ...
Ecterion's user avatar
3 votes
0 answers
1k views

Can we combine multiple different neural networks in one?

I want to make a kind of robotic brain, i.e. a big neural network, which includes an NLP model (for understanding human voice), real-time object recognition system (so that it can identify particular ...
Rahul Vansh's user avatar
2 votes
0 answers
48 views

Should intelligent machines have a body? (Reference request)

I was studying AI when a question came to my mind. I have to write a 6-pages essay on a chosen topic in AI, and I think it can be interesting to reflect on the measure in which machines should have a ...
Amanda Wealth's user avatar
2 votes
0 answers
72 views

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 ...
Ziofil's user avatar
  • 128
2 votes
0 answers
30 views

What are some non-RL-based approaches to solving a typical bin assignment problem?

What are some non-RL-based approaches to solving a typical bin assignment problem, i.e., given a set of items (can be multidimensional), find the bin/knapsack/target which best packs (with minimum ...
helloworld's user avatar
2 votes
0 answers
533 views

Is there a literature on the time complexity of Neural Networks?

There exist various blog posts describing the time complexity of Fully Connected Neural Networks (1, 2, 3, 4); Convolutional Neural Networks (CNN) (5) and of Long Short-Term Memory (LSTM) networks (6)....
Daniel's user avatar
  • 21
2 votes
0 answers
144 views

Today's Practicality of Bayesian Neural Networks

Just having heard lately about BNNs (wow, ANNs and CNNs are clear; now there's a B? What's that? Ahh, Bayesian ;-)) and quickly getting their main idea and focus, that is, weights not being pure ...
Mathy's user avatar
  • 143
2 votes
2 answers
1k views

Why does triplet loss allow to learn a ranking whereas contrastive loss only allows to learn similarity?

I am looking at this lecture, which states (link to exact time): What the triplet loss allows us in contrast to the contrastive loss is that we can learn a ranking. So it's not only about similarity, ...
Gulzar's user avatar
  • 769
2 votes
2 answers
1k views

What are the state-of-the-art AI methods to recognize elements on webpages or the purpose of webpage?

I'm curious to know about the capabilities of AI today in 2022. I know that AI has become pretty good at recognizing things like objects in photos. But what about when it comes to elements in HTML? ...
kenshin9's user avatar
  • 121
2 votes
0 answers
292 views

Why does TD (0) converge to the MLE solution of the Markov model?

Why does TD (0) converge to the MLE solution of the Markov model? Let's take the Example 6.4 in Sutton and Barto's book as an example. Example 6.4: You are the Predictor Place yourself now in the ...
XXX's user avatar
  • 143
2 votes
0 answers
560 views

Did the unsolved XOR problem in "Perceptrons: An Introduction to Computational Geometry" 1969 book really cause the winter of the AI in 1974?

Winter of AI definition: periods of reduced funding and interest in artificial intelligence research, due to unmet expectations after a period of hype. There have been at least two major AI winters ...
rubengavidia0x's user avatar
2 votes
0 answers
101 views

Has the idea of using different learning rates for different layers been explored in the literature?

I wonder whether there are heuristic rules for the optimal selection of learning rates for different layers. I expect that there is no general recipe, but probably there are some choices that may be ...
spiridon_the_sun_rotator's user avatar
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 ...
Verónica Rmz.'s user avatar
2 votes
1 answer
400 views

How could Bayesian neural networks be used for transfer learning?

In transfer learning, we use big data from similar tasks to learn the parameters of a neural network, and then fine-tune the neural network on our own task that has little data available for it. Here, ...
samsambakster's user avatar
2 votes
0 answers
104 views

What is the effect of K in K-NN on the VC dimension?

What is the effect of K in K-NN on the VC dimension? When K increases, is the VC dimension decreased or increased, or we can't say anything about this? Is there a reference book that discusses this?
robot learning's user avatar
2 votes
0 answers
41 views

What is the paper that states that humans incorrectly trust the incorrect explanations of the AI?

I was reading a paper on the subject of explainable AI and interpretability, in particular the tendency of people (even experts) to excessively trusting explanations given by AI. In the intro the ...
Stoaty193's user avatar
2 votes
0 answers
56 views

What is the first short film completely made by AI?

I have created (not me exactly) a short film entirely made by AI. There many short films (like Sunspring) 'written' by AI but were acted out by humans. In my short film, the story is by the AI, the ...
AnanthaKrishna K's user avatar
2 votes
0 answers
28 views

What are some of the main high level approaches to applying ML on kinematic sensor data?

I've just started a project which will involve having to detect certain events in a stream of kinematic sensor data. By searching through the literature, I've found a lot of highly specific papers, ...
Alexander Soare's user avatar
2 votes
0 answers
143 views

Are there any new weight initialization techniques for DNN published after 2015?

Considering weights initialization in my personal projects, I always used some standard techniques such as: Glorot (also known as Xavier) initialization (2010). Mertens initialization (2010). He ...
Stefano Barone's user avatar
2 votes
0 answers
36 views

Can DQN outperform DoubleDQN?

I found a similar post about this issue, but unfortunately I did not find a proper answer. Are there any references where DQN is better than DoubleDQN, that is DoubleDQN does not improve DQN ?
ddaedalus's user avatar
  • 919
2 votes
2 answers
287 views

Model-based RL for time series data

I have time-series data. When I take an action, it impacts the next state, because my action directly determines the next state, but it is not known what the impact is. To be concrete: I have $X(t)$ ...
Mariam 's user avatar
2 votes
0 answers
689 views

What are the differences between Proximal Policy Optimization versions PPO1 and PPO2?

When Proximal Policy Optimization (PPO) was released, it was accompanied by a paper describing it. Later, the authors at OpenAI introduced a second version of PPO, called PPO2 (whereas the original ...
Daniel B.'s user avatar
  • 825
2 votes
0 answers
36 views

Literature on the advantages of using an auto-encoder for classification

Given a supervised problem with X, y input pairs, one can do two things for obtaining the function f that maps X with y with Neural Networks (and in general in machine learning): Deploy directly a ...
Tommaso Bendinelli's user avatar
2 votes
0 answers
175 views

Combine DQN with the Average Reward setting

I have to deal with a non-episodic task, where there is addittionally a continuous state space and more specifically in each time step there is always a new state that has never been seen before. I ...
ddaedalus's user avatar
  • 919
2 votes
0 answers
86 views

Forcing a neural network to be close to a previous model - Regularization through given model

I'm wondering, has anyone seen any paper where one trains a network but biases it to produce similar outputs to a given model (such as one given from expert opinion or it being a previously trained ...
ABIM's user avatar
  • 565
2 votes
0 answers
84 views

What is the proof that the variance of the gradient estimate in Actor-Critic is smaller than in REINFORCE?

The intuition provided when introducing actor-critic algorithms is that the variance of its gradient estimates is smaller than in REINFORCE as, e.g., discussed here. This intuition makes sense for the ...
Igor's user avatar
  • 121
2 votes
0 answers
57 views

Is there a tutorial for beginners on capsule neural networks?

I am interested in capsule neural networks. I have already read the paper Dynamic Routing Between Capsules, but it is a little bit difficult to follow. Is there a tutorial for beginners on capsule ...
Hiren Namera's user avatar
2 votes
0 answers
43 views

What are the applications of hierarchical softmax?

Apart from its use in word embeddings (e.g word2vec algorithm), are there any other applications of hierarchical softmax? If yes, can you please give me some reference papers?
ddaedalus's user avatar
  • 919
2 votes
0 answers
28 views

Is there any published research on the information-carrying capacity of the human face?

Is there any published research on the information-carrying capacity of the human face? Here I mean "how much information can be conveyed via facial expressions & micro-expressions". This is a ...
DukeZhou's user avatar
  • 6,237
2 votes
0 answers
47 views

Is there an online RL algorithm that receives as input a camera frame and produces an action as output?

I want to build a reinforcement learning model, which takes a camera picture as input, that learns online (in terms of machine learning). Based on the position of an object on the camera, I want the ...
Wuuhi's user avatar
  • 21
2 votes
0 answers
83 views

When to do discretization to decrease the state/action space in RL?

When to do discretization to decrease the state/action space in RL? Can you give me some references that such a technique is used?
ddaedalus's user avatar
  • 919
2 votes
0 answers
410 views

What is the original source of the TD Advantage Actor-Critic algorithm?

What is the original source of the TD Advantage Actor-Critic algorithm? I found this tutorial really helpful for learning the algorithm. However, what is the original source of this algorithm?
C.Neal's user avatar
  • 121
2 votes
0 answers
41 views

Is there a theory that captures the following ideas?

A big class of problems that are relevant in today's society are full of uncertainty and are also sometimes computationally intractable. Along our lives we come to realize that we are solving the same ...
Vyraj's user avatar
  • 131
2 votes
0 answers
33 views

Will structured knowledge bases continue to be used in question answering with the likes of BERT gaining popularity?

This may come across as an open and opinion-based question, I definitely want to hear expert opinions on the subject, but I am also looking for references to materials that I can read deeply. One of ...
AndyM's user avatar
  • 121