Questions tagged [models]
For questions related to modelling external environment, functional models tuned through convergent methods such as artificial networks or fuzzy logic containers, loss models, semantic models, model-based reasoning, or other kinds of models used in AI research, development, or practice.
127
questions
0
votes
1
answer
32
views
Can software testers transfer their skills into adversarial testing for AI/LLMS?
My sincere apologies if I am more asking for advice, rather than a solution to a specific problem. However, I am trying to survive in this new world as a software tester. I have been doing test ...
0
votes
0
answers
36
views
Learning Rate greater than ~0.00005 significantly hinders model performance and increases loss
I have been trying to train a model with 0.001 learning rate. I tried regression techniques, early stopping and lr manipulations within epochs. But nothing felt right even though after numerous tries ...
0
votes
1
answer
53
views
Are there any machine learning frameworks, other than Statistical Decision Theory which proposes a loss function, for developing models?
In Elements of Statistical Learning, the authors present a framework called statistical decision theory that employs a loss function for choosing $f(X)$ to predict $Y$:
$$EPE(f) = E(L(Y, f(X)))$$
Can ...
0
votes
1
answer
29
views
Input size for a RNN layer by modeling a dynamical system
I'm trying to understand the concept of dynamical system with NN by studying this very well explanation here.
But I stuck in the following problem:
The author uses a RNN and/or a LSTM network as a NN ...
0
votes
0
answers
8
views
How do nonlinear relationships affect casuality determination
Let's assume that I have only one independent variable and one dependent, and
I have a great model with minimal error which deals well with predicting.
Let's also assume that I do no know the true ...
0
votes
0
answers
9
views
Trying to use my first created Knowledge graph embeddings model
I'm trying to learn about creating and using knowledge graph embeddings models, I got a code, adapted it until I got no compiling or executing errors but now the predictions it mades are wrong. This ...
0
votes
2
answers
42
views
What might be the suitable machine learning algorithm to train a model suitable for forecasting a patient's urine output?
The task involves developing a machine learning model trained on urine output trends, clinical parameters, medications, and fluid input of patients to predict their future urine output.
What machine ...
0
votes
0
answers
30
views
What reference documents exist for LLM inference engines and models?
For example, vllm is an inference engine, and according to their roadmap they will incororate vllm into several LLM API engines such as openllm, rayserve, and nvidia triton.
What are examples of ...
0
votes
0
answers
15
views
Periodic feature layer for Lotka-Volterra approximation
I am working with DeepXDE, a SciML library that can be used to solve differential equations. I came across this demo page for solving a Lotka-Volterra system. Since the solutions are known to be ...
0
votes
1
answer
43
views
chained linear regression models vs feed forward NN
I am trying to understand the difference between feedforward NN and chained linear regression models, if and why they can model nonlinear functions.
both are able to model non-linear dependencies
...
1
vote
0
answers
23
views
Is there a standard nomenclature for model names suffixed by strings such as "Q4_K_S"?
Many models specify details using prefixes such as Q6_K or Q4_K_S.
It seems obvious that the ...
-1
votes
1
answer
30
views
0
votes
0
answers
22
views
AI model for transitioning between states
I have no knowledge and background in AI. I am however interested in a task, and was wondering if there might be some AI models, which are suitable for this kind of tasks: imagine we have two (...
0
votes
1
answer
37
views
What task/model to use to locate textblock in pdf that matches regulation rules
I have a PDF written to disclose different corporate policies and governance implementations. It's a lot more but you get the gist.
On the other hand, I have a set of rules and regulations that ...
0
votes
0
answers
66
views
Neural network dynamic input shape vs fixed input shape in input layer for handling NULL values
I have binary classification problem, we know that the output layer will be scalar or dense a.k.a. 1 unit neuron with sigmoid as function activation. 1 means is the subject will die, while 0 means ...