All Questions
678 questions
1
vote
1
answer
24
views
How do neural scaling laws explain the improvements from LSTMs to Transformer based models
I was reading about a study on neural scaling laws from 2017 and they noted this as a summary. From Hestness, Joel; Narang, Sharan; Ardalani, Newsha; Diamos, Gregory; Jun, Heewoo; Kianinejad, Hassan; ...
- 279
0
votes
0
answers
37
views
When should you use a transformer and when LSTM, GRU and other Neural Networks?
There is a lot of information on the Internet that the transformer is better than RNN in everything, but is it true?
Examples:
«What if I need to translate words?»
«Generate text, images?»
«Play a ...
2
votes
1
answer
26
views
Do we plug in the old values or the new values during the gradient descent update?
I have a scenario when I am trying to optimize a vector of D dimensions. Every component of the vector is dependent on other components according to a function such as: summation over (i,j): (1-e(x_i)(...
1
vote
1
answer
49
views
Why doesn’t this optimization method work?
My idea is simple, for a loss function $L$, learning rate $\alpha$ and weights $W_n$ define the function $u_n(\alpha)$ as:
$$u_n(\alpha) = L(W_n - \alpha \nabla_n L)$$
If we find the minimum of $u_n$, ...
- 173
1
vote
0
answers
22
views
Optimizing Wind Park Layout Using Direct Action-to-Input Mapping
I’m optimizing a black-box objective function where the task is to find the optimal turbine locations in a wind park. Previously, I used a PPO reinforcement learning approach with a step-by-step ...
- 23
2
votes
1
answer
195
views
What Are the Computational Complexity Bounds for Dynamic Programming in Reinforcement Learning?
I’m currently reading "Reinforcement Learning: An Introduction" by Sutton and Barto, and I have a question regarding the computational complexity of Generalized Policy Iteration (GPI) in ...
- 660
0
votes
2
answers
55
views
Is there any actual difference between these 2 definitions of a state value function?
The definition of the value function in TRPO paper is
\begin{align}
V_\pi(s_t) &= \mathbb{E}_{a_t,s_{t+1},\ldots} \left[ \sum_{l=0}^{\infty} \gamma^l r(s_{t+l}) \right], \\[10pt]
a_t &\sim \pi(...
- 139
1
vote
0
answers
19
views
Why won't my aerodynamics neural network converge?
I am training a neural network to predict the aerodynamic properties of an airfoil given 6 shape parameters, the angle of attack, and the Reynolds number. I have scraped about 120MB of training data ...
- 11
0
votes
0
answers
14
views
Neural Network not targeting any particular output but using backpropagation to shapes input
I don't know if that exists or how is that called, but can I make a Neural Network to adapt directly the input from an error function?
Assume I have 2 complex(I mean hard to compute, domain still in ...
- 301
0
votes
0
answers
15
views
Backpropagation with rasterization step
I have an odd little problem facing me for my project.
I have a smooth polygon defined by parameters.
I have convolution transformation, similar to a Gaussian blur. This transformation can only be ...
- 11
1
vote
1
answer
30
views
Generalization comparison between MBGD-M, RMSprop and Adam
I am currently training a 3D CNN classifier on preprocessed EEG data. I tried 3 optimization algorithms for comparison, namely Mini-Batch Gradient Descent with Momentum (MBGD-M), RMSprop, and Adam. ...
- 11
0
votes
0
answers
15
views
Is there a workaround to avoid using heavy for loop to calculate each item's loss in the batch for my code?
I am currently working with a gaussian splatting codebase that projects points and performs rasterization for one single image. Because of this, since I am doing this for multiple images (batched), I ...
- 101
0
votes
0
answers
25
views
Optimization on predicted confidences
I currently have a classification task, except I use an object detection model. The model outputs detections for all objects it locates in the image, and assigns a confidence to each. However, I am ...
0
votes
0
answers
10
views
Implementation of the diversity strategy of MSCPSO
The Multi-Swarm Self-Adaptive and Cooperative Particle Swarm Optimization algorithm (MSCPSO) from this paper mentions a diversity strategy to enable better exploration capabilities over the standard ...
- 1
1
vote
1
answer
118
views
Custom Loss Function Traps Network in Local Optima
I am working with a feedforward neural network to fit the following simple function:
N(1) = -1
N(2) = -1
N(3) = 1
N(4) = -1
But I don't want to use the Mean-...
- 11
2
votes
1
answer
38
views
Is there a better way to do this type of optimization?
I have an image classification task that uses an object detection model as its basis. For each image, I get a vector of confidences (one value for each class), and I take the class with the highest ...
- 21
2
votes
2
answers
897
views
Why isn’t this formula used at all?
$$ w_{n+1} = w_n - \alpha \frac{f \nabla f}{||\nabla f||^2} $$
It calculates where the line that’s in the same direction as gradient and has $f$’s slope in that direction becomes zero.
In one ...
- 173
0
votes
0
answers
20
views
Combination of components to maximize a multi-criteria objective function
I have been given a list of components, with various “contributions” (or weights) which put together in a weighted combination have a combined aggregate effect. I then have the task of suggesting ...
- 101
0
votes
1
answer
108
views
Does Machine Learning focus on discriminative AI while Deep Learning also focus on generative AI?
I know that Deep Learning is subset of Machine learning
But is it correct that classical ML algorithms mainly focus on implementing Discriminative AI while DL algorithms implement both Generative AI ...
- 181
3
votes
1
answer
36
views
Different Definitions of Momentum -- which one should I work with?
I'm seeing different manners to define momentum, I'm not sure if there is significant difference or not.
From my thinking, they seem to do a similar thing mathematically and in practice but I'm ...
- 125
1
vote
1
answer
68
views
Why are neural networks optimized instead of just optimizing a high dimensional function?
I know that neural networks are universal approximators when given a sufficient number of neurons, but there are other things that can be universal approximators, such as a Taylor series with a high ...
- 11
2
votes
0
answers
70
views
Can local learning rules minimize a global loss?
It is widely believed that synaptic plasticity is the way biological brains learn. Artificial implementations of this mechanism are for instance local weight-update rules in Spiking Neural Networks. ...
- 121
0
votes
2
answers
107
views
What do we mean by "AI is correlated"?
From Wikipedia
Causal AI is a technique in artificial intelligence that builds a causal model and can thereby make inferences using causality rather than just correlation. One practical use for ...
- 117
1
vote
0
answers
27
views
Why completely two different algorithms are being used in Deep Q Learning?
I'm a new student in reinforcement learning. Recently, I've been studying about different algorithms of RL. But I'm quite surprized that there are some algorithms which are named as "same" ...
0
votes
1
answer
36
views
How to find an argument of a NN function(which returns a distribution) to minimize a KL divergence?
Consider a neural network function $f:\mathbb{R}\to distribution$. For simplicity, maybe consider that it returns a gaussian distribution.
I want to find $\arg\min_{s\in\mathbb{R}}D_{KL}(f(s),q)$ for ...
- 45
0
votes
0
answers
14
views
Adaptive regret bounds in Online Convex Optimization
I have recently stumbled upon a proof in Elad Hazan's book "Introduction to Online Convex Optimization" with a step I can't quite grasp.
In the second to last line it is not clear to me why ...
1
vote
1
answer
35
views
Confusion about Adagrad/Rmsprop/Adam about the direction of change
Hello I'm learning optimizers now, I can understand the momentum part (similar to physics world), but confused about different learning rate of different parameters,
for Adagrad/Rmsprop, if $∂L/∂w_1$ ...
- 111
2
votes
2
answers
556
views
Is it easier to use back-propagation or genetic algorithms to teach an artificial intelligence?
I am making a very simple neural network for a school project, and I would like to know what the best and easiest way to "teach" a neural network would be. From what I know, backpropagation ...
- 23
0
votes
0
answers
21
views
Are there leaderboards/tables/stats that compare inference times between close-sourced LLMs such as GPT 3.5/4 and Claude?
https://huggingface.co/spaces/optimum/llm-perf-leaderboard is great to compare inference times between LLMs but it misses close-sourced LLMs such as GPT 3.5/4 and Claude.
- 3,267
1
vote
1
answer
98
views
Why does Multi Objective RL exist?
I have recently posted a question here about a problem that I have controlling a robotic arm.
Basically I have a dense reward for the arms position, and a sparse reward for the arms stiffness: Reward ...
- 43
1
vote
0
answers
125
views
Reward shaping for dense and sparse rewards
I am working on an RL Problem that drives me nuts.
My goal is to control a robot arm in a simulator that has to do 2 things:
Hold the arm in a certain position (that is easy and done)
If I apply an ...
- 43
1
vote
2
answers
1k
views
What is the difference between densenet and resnet?
Is the only difference between the two how the skip connection is combined? Resnet combines skip connections through addition and Densenet through concatenating.
The Densenet paper appears to be ...
- 233
0
votes
1
answer
37
views
How to estimate Time vs Memory trade-off prior to modelling
It is often the case when the time vs memory trade-off is underestimated prior to using ML/DL for solving a particular task. Taking into account the type, size and format of the available data and ...
- 1
2
votes
1
answer
66
views
Can you explain the Hinton's comment "Rprop is equivalent to using the gradient, but also dividing by the size of the gradient"?
Been reviewing some old foundational material and ran into this comment by Hinton on Rprop in his old Coursera class:
Rprop is equivalent to using the gradient, but also dividing by the
size of the ...
- 121
1
vote
1
answer
98
views
Is there any advantage of genetic algorithm (or programming) over Neural Networks? [closed]
I am planning to switch from neural networks to genetic algorithms (GA) and programming (GP).
One of the main hassles of working with neural networks is that it requires a large amount of training ...
- 339
0
votes
0
answers
40
views
Non differentiable loss function train with actor critic style
I'm working on a project where a non differentiable loss is there. I'm thinking about how should I deal with them.
My model is a very big lstm model (about 1M parameter), and after 500 steps (not sure ...
- 13
1
vote
1
answer
103
views
The SOTA of derivative-free optimization
As titled, I want to ask what is the SOTA of derivative-free algorithm.
I am not familiar with this thing at all, the only derivative-free optimization algorithm I am familiar with is GA, and others ...
- 13
0
votes
2
answers
61
views
Should I define my problem as image segmentation or detection?
I have a problem and have to decide wether it's an object detection or object segmentation problem. I want to use Yolov8 for training. We already have hundrets of images but they aren't labeled yet. ...
- 113
0
votes
1
answer
45
views
How to prevent update a pretrained model if a model is optimized with backpropagation? [closed]
These are components in my model:
A generator
An encoder: a pretrained, and should not updated.
A loss function.
Input is passed to the encoder to generate X, X is then passed to generator to ...
- 109
1
vote
0
answers
67
views
Finding resulting domains after enforcing arc consistency
This question is about the below exam scheduling constraint satisfaction graph, where each node represents a course. Each course is associated with an initial domain of possible exam days (most ...
- 11
1
vote
1
answer
1k
views
When to use Pruning, Quantization , Distillation and others when optimizing speed
I want to understand how to optimize models for inference speed and am seeking some advice and best practices for the same.
I am a little bit aware of the concepts of pruning, quantization, and ...
- 789
4
votes
2
answers
3k
views
What are the differences between seq2seq and encoder-decoder architectures?
I've read many tutorials online that use both words interchangeably. When I search and find that they are the same, why not just use one word since they have the same definition?
user78615
1
vote
1
answer
133
views
Why are these two implementations of the $\epsilon$-greedy policy different?
According to the book Reinforcement Learning An Introduction, the epsilon greedy policy can generally implemented as:
$$
\pi(a|s) =
\begin{cases}
\frac{\epsilon}{|A|} + 1 - \epsilon & \text{if } ...
- 195
2
votes
1
answer
541
views
What are the similarities between Q-learning and Value Iteration?
This is the explanation of value iteration in our notes where you keep applying bellman optimality equation till it stops changing and then acting greedily wrt the value function gives the optimal ...
- 23
1
vote
0
answers
70
views
When can we unnest the minimizations/recursions in an value function(bellman optimality equation)?
When reading the following paper(page 4): An Approximate Dynamic Programming Approach
for Dual Stochastic Model Predictive Control
I could see that they were able to unnest the minimization's in the ...
- 11
1
vote
0
answers
71
views
Is this a bandit problem or a MDP?
I am trying to understand if this problem can be casted both as a bandit problem as well as an MDP.
Lets assume that we are trying to optimize sales $y_t$ based on investments $x_{1, t}, x_{2, t}$ ...
- 53
1
vote
1
answer
48
views
Is there validation data in K-fold cross-validation?
We know that in machine learning the dataset is divided into 3 parts: training data, validation data and test data.
On the other hand, K-fold cross-validation is defined as follows:
the dataset is ...
- 1,115
2
votes
1
answer
423
views
How to train a sample weight model for another ML model?
I'm trying to train a ML model, however the predictability of the different samples varies, i.e. some samples are inherently much harder to predict/estimate than others. Poorer predictions for these ...
- 123
0
votes
1
answer
247
views
What is the difference between Machine Learning model, algorithm and hypothesis?
I'm fairly new to Machine Learning field and still to grasp the basics, so this question may seem very stupid, but what is the difference between Machine Learning model, algorithm and hypothesis?
Like ...
1
vote
1
answer
38
views
Applicability of Holland's Schema Theorem to Genetic Algorithms with Non-Binary Individual Representations
I'm currently working on a problem formulation that requires non-binary individual representations in a genetic algorithm (GA). I've been exploring Holland's Schema Theorem as a theoretical basis for ...
- 11