All Questions
678 questions
0
votes
0
answers
28
views
Resolving Derivation Discrepancies for Differentiating through Optimization Paths
I'm reading the paper "Optimizing Millions of Hyperparameters by Implicit Differentiation". The key contribution of the paper is to show that you can replace optimizing through the ...
- 1
2
votes
2
answers
3k
views
What are the differences between BLEU and METEOR?
I am trying to understand the concept of evaluating the machine translation evaluation scores.
I understand how what BLEU score is trying to achieve. It looks into different n-grams like BLEU-1,BLEU-2,...
- 373
1
vote
0
answers
38
views
Structured policies in dynamic programming: solving a toy example
I am trying to solve a dynamic programming toy example. Here is the prompt: imagine you arrive in a new city for $N$ days and every night need to pick a restaurant to get dinner at. The qualities of ...
- 11
1
vote
2
answers
1k
views
What is the difference between a policy and rewards?
I don't understand the difference between a policy and rewards. Sure, a policy tells us what to do, but isn't the output of a neural network trained on rewards basically a policy (i.e. choose the ...
0
votes
1
answer
1k
views
What is the difference between CNN-LSTM and RNN?
I'm starting to study RNN for a project of video prediction, but I encounter these CNN-LSTM models. Initially, I thought that is another name for RNN, but I think I get it wrong. Since I'm a beginner ...
3
votes
3
answers
1k
views
Why are Siamese Neural Networks used instead of a single neural network?
Siamese Neural Networks are a type of neural network used to compare two instances and infer if they belong to the same object. They are composed by two parallel identical neural networks, whose ...
- 63
2
votes
0
answers
28
views
What are the benefits of using spectral k-means over simple k-means?
I have understood why k-means can get stuck in local minima.
Now, I am curious to know how the spectral k-means helps to avoid this local minima problem.
According to this paper A tutorial on Spectral,...
- 121
2
votes
0
answers
119
views
When to model decision-making problem as single agent vs multi-agent problem?
I understand the goals and purposes of RL in the case of a single agent and the underlying model, i.e. MDPs, for RL problems (or sequential decision making with uncertainty in general).
My question is ...
- 121
8
votes
2
answers
10k
views
What is the difference between a loss function and reward/penalty in Deep Reinforcement Learning?
In Deep Reinforcement Learning (DRL) I am having difficulties in understanding the difference between a Loss function, a reward/penalty and the integration of both in DRL.
Loss function: Given an ...
- 195
1
vote
0
answers
191
views
Best algorithm for the Word Ladder puzzle
What would be the best performing algorithm to solve the Word Ladder problem, in terms of guaranteed finding of the shortest solution in the shortest possible time? Is it BFS, DFS, A*, IDA* or another ...
- 11
3
votes
1
answer
2k
views
What is the difference between a greedy policy and an optimal policy?
I am struggling to understand what is the difference between an optimal policy and a greedy policy.
Let $F(r_{t+1},s_{t+1}| s_t,a_t)$ be the probability distribution accorting to which, given action $...
- 33
3
votes
1
answer
2k
views
What is multi-head attention doing mathematically, and how is it different from self-attention?
I'm trying to understand the difference between the concept of self-attention and multi-head attention. The latter is not actually too clear to me.
I understand that, in the case of self-attention, we ...
- 307
1
vote
0
answers
63
views
How to compare RL algorithms with different NN sizes?
I wanted to run some tests with some RL algorithms in a continuous control task, namely PPO-clip and SAC.
When comparing their NN structures described in their papers, SAC used 2 layers with 256 ...
- 119
3
votes
1
answer
157
views
Why does my regression-NN completely fail to predict some points?
I would like to train a NN in order to approximate an unknown function $y = f(x_1,x_2)$. I have a lot of measurements $y = [y_1,\dots,y_K]$ (with K that could be in the range of 10-100 thousands) ...
- 31
1
vote
1
answer
36
views
Additional Optimizations for Convolutional Models On Inferencing
I am aware of several ways to optimize a convolutional (or any) model after training to make inferencing quicker. I am currently implementing BatchNormalization Folding and removing Dropout layers ...
- 113
-2
votes
2
answers
124
views
What does it mean by Generalization? [closed]
Towards Theoretically Understanding Why SGD Generalizes Better Than ADAM in Deep Learning
What does it mean by Generalization in this article?
- 339
0
votes
1
answer
60
views
Are Problems in AI Usually "Ill Posed"?
I was reading the following link (https://en.wikipedia.org/wiki/Well-posed_problem) on "Well Posed Problems". Supposedly, if a problem is "Well Posed", it must meet the following ...
- 339
1
vote
0
answers
91
views
Are Bayesian Optimization Methods Better Suited Noisy Optimization Problems?
We know that in many applied contexts (e.g. Machine Learning, Loss Functions for Neural Networks), the functions we are trying to optimize are "noisy" by definition (unlike in the classical ...
- 339
1
vote
2
answers
2k
views
Effects of ReLU Activation on Convexity of Loss Functions
I have heard the following argument being made regarding Neural Networks:
A Neural Network is a composition of several Activation Functions
Sigmoid Activation Functions are Non-Convex Functions
The ...
- 339
0
votes
0
answers
50
views
What I Should Do to Reduce Solution Size for Simulated Annealing Algorithm?
I am trying to find the best solution for radar placement problem with using multi objective simulated annealing algorithm.
So there is an area (in real map) and I want to put minimum count of radar ...
1
vote
0
answers
242
views
Why does the schema theorem of genetic algorithms hold?
I have been reading about the Schema Theorem - one of the first theorems from the field of evolutionary computing and genetic algorithms, largely responsible for justifying the use of genetic ...
- 339
2
votes
1
answer
240
views
Is logic AI a complement to learning AI?
I want to know the relation between logic AI and learning AI.
Logic AI here refers to the branch of AI that is based on mathematical logic. Learning AI refers to the branch of AI that is based on ...
- 3,990
2
votes
2
answers
129
views
Does reaching the global optima guarantee good performance in a task?
It is to my understanding that, in deep learning, we are essentially trying to minimize the loss function that we have defined and reach its global optima through some form of optimization technique. ...
- 153
1
vote
1
answer
1k
views
What is the difference between Mean Teacher and Knowledge Distillation?
I recently read two papers:
BYOL Bootstrap your own latent: A new approach to self-supervised Learning
DINO Emerging Properties in Self-Supervised Vision Transformers.
I am confused about the terms ...
0
votes
1
answer
138
views
How many layers and neurons in a FFNN do I need to make it equivalent to a CNN?
I started to learn machine learning early, and I studied the convolutional neural network and its ability to understand images and how it helps to reduce the number of parameters that need to be tuned....
13
votes
2
answers
2k
views
Is there a fundamental difference between an environment being stochastic and being partially observable?
In AI literature, deterministic vs stochastic and being fully-observable vs partially observable are usually considered two distinct properties of the environment.
I'm confused about this because what ...
- 255
1
vote
0
answers
88
views
a loss for binary step function data
I have some data with ground truth that looks like a binary step function, where part of it is 0 and part is one.
An example for the GT can be like ...
- 111
2
votes
1
answer
74
views
Can teacher forcing in RNN ensure Turing completeness?
RNN has the same capability as a universal Turing machine. But I am confused whether RNN holds the same capabilities if we use teacher forcing.
Consider the following excerpts from paragraphs taken ...
- 3,990
0
votes
0
answers
139
views
Why is there a Hessian diagonal approximation? And when can we use it?
This topic has been introduced in "Pattern Recognition and Machine Learning, Bishop, 2006", section 5.4.1. I am a bit confused about this method and I have two questions.
Why this method ...
1
vote
0
answers
81
views
Is the capability of RNN more than the capability of MLP?
Consider the following excerpt paragraph taken from the section titled "Recurrent Neural Networks" of the chapter 10: Sequence Modeling: Recurrent and Recursive Nets of the textbook named ...
- 3,990
4
votes
1
answer
255
views
Is there any relation between the recursive neural network and recurrent neural network?
Recurrent neural networks, abbreviated as RNNs, are widely used in deep learning literature, especially for text processing.
Are they related to recursive neural networks in any way?
I am asking for ...
- 3,990
1
vote
1
answer
270
views
Are the capabilities of connectionist AI and symbolic AI the same?
The universal approximation theorem says that MLP with a single hidden layer and enough number of neurons can able to approximate any bounded continuous function. You can validate it from the ...
- 3,990
1
vote
1
answer
385
views
What is meant by "two action selections" in SARSA?
I have some difficulties understanding the difference between Q-learning and SARSA. Here (What are the differences between SARSA and Q-learning?) the following updating formulas are given:
Q-Learning
$...
- 266
5
votes
1
answer
856
views
What is the difference between an on-policy distribution and state visitation frequency?
On-policy distribution is defined as follows in Sutton and Barto:
On the other hand, state visitation frequency is defined as follows in Trust Region Policy Optimization:
$$\rho_{\pi}(s) = \sum_{t=0}^...
- 379
2
votes
1
answer
460
views
How do I use machine learning to create an optimization algorithm?
Let's say that I want to create an optimization algorithm, which is supposed to find an optimum value for a given objective function. Creating an optimization algorithm to explore through the search ...
- 23
0
votes
0
answers
38
views
Is there a way to adapt Particle Swarm Optimization to an incremental/online learning setting?
As stated in the title, is there a way to adapt PSO to an online scenario where new data samples arrive continuously?
In more detail: suppose that I have a classifier with several parameters for which ...
- 1
4
votes
2
answers
312
views
Are Genetic Algorithms suitable for a problem with a non-unique optimal solution?
I was wondering if a genetic algorithm is useful if the optimization problem has several optimal solutions.
My thought was that I should not use it since when combining two members of a population who ...
- 141
6
votes
1
answer
2k
views
When to use the state value function $V(s)$ and when to use the state-action value function $Q(s, a)$?
I saw the difference between value function $V(s)$ and $Q(s, a)$. But when do I use each one? When I coded in Matlab I only used $Q(s, a)$ directly (as I was thinking of a tabular approach). So, when ...
8
votes
2
answers
6k
views
Why is gradient descent used over the conjugate gradient method?
Based on some preliminary research, the conjugate gradient method is almost exactly the same as gradient descent, except the search direction must be orthogonal to the previous step.
From what I've ...
- 1,406
2
votes
2
answers
208
views
How will MLOps and lifelong learning be complementary?
According to [1], in MLOps, continuous training is
a new property, unique to ML systems, that's concerned with automatically retraining and serving the models.
While lifelong/incremental learning ...
- 967
2
votes
0
answers
153
views
What is the difference between Probabilistic Graphical models and Graph Neural networks?
While going over PGMs and GNNs, it seems like both leverage the graph data structure. The former has been used to represent causal associations (among other things), while the latter has a varied set ...
- 670
1
vote
0
answers
61
views
Multi-armed Bandit in optimization on graph edges selection
I have the problem, which I described below. I wonder if there exists a class of multi-armed bandit approaches that is related to it.
I am working on computer networking optimization.
In the simplest ...
- 21
1
vote
1
answer
661
views
How is the VAE related to the Autoencoding Variational Bayes (AEVB) algorithm?
I am familiar with the variational autoencoder, but not totally clear on what exactly the AEVB is.
In the original VAE paper (by Kingma and Welling), he uses both the terms variational autoencoder and ...
- 243
0
votes
1
answer
128
views
In this example of fuzzy c-means, what is the difference between "sigma" and "center" for the clusters?
In this example, what exactly do "Cluster" and "Sigma" mean? (They chose random coordinates for the three centroids of the groups)
Centers: Cluster centers, returned as a ...
- 121
1
vote
0
answers
102
views
Why are optimization algorithms for deep learning so simple?
From my knowledge, the most used optimizer in practice is Adam, which in essence is just mini-batch gradient descent with momentum to combat getting stuck in saddle points and with some damping to ...
- 133
1
vote
1
answer
2k
views
What is uncentered variance and how it becomes equal to mean square in Adam?
I have been reading about Adam and AdamW (Here). The author mentioned that in "uncentered variance" we don't consider subtracting mean
In this statement, the author is talking about ...
- 151
1
vote
1
answer
338
views
What is the difference between "Syllogism" and "Law of Syllogism"?
The logical arguments are the basis for Artificial Intelligence. That is why I picked AI community to ask my question.
Reading from Wikipedia,
A syllogism is a kind of logical argument that applies ...
- 13
2
votes
1
answer
173
views
Closed networks vs Networks with a removed delay to predict new data
I've come across two types of neural networks to predict, both from Matlab, the closed structure and the net that removes one delay to find new data.
From Matlab's app generated scripts we see:
% ...
6
votes
2
answers
8k
views
When to use Value Iteration vs. Policy Iteration
Both value iteration and policy iteration are General Policy Iteration (GPI) algorithms. However, they differ in the mechanics of their updates. Policy Iteration seeks to first find a completed ...
- 541
1
vote
0
answers
36
views
How do you decide that you have tested enough hyper-parameter combinations for a specific neural network architecture?
How do you decide that you have tested enough hyper-parameter combinations for a specific neural network architecture to discard it and move on to a new model?
Do you have a structured (generic) ...
- 11