All Questions
12,028
questions
0
votes
0
answers
7
views
0
votes
0
answers
6
views
Classical architecture of autoencoder neural networks
I want to try Autoencoders(AE) (not variational) with a PINNs. The AE will be to encode the points of the domain. Lets say the variable domain (time-space + parameter space) dimension is n where n is ...
- 1
0
votes
0
answers
24
views
Can you illustrate how the weights in transformer model generated from a training sentence can be generalized to an unseen test sentence?
Can you show how the weights in transformer model are generalizable?
- 101
0
votes
0
answers
25
views
Intentionally corrupting LLM weights (lobotomy)
It is largely unknown how LLMs work inside. Has anyone scientifically tried to corrupt (open source) model's weights in an organized manner to maybe detect which parts of the model are doing what or ...
- 271
1
vote
0
answers
9
views
Neural network architecture or code for style transfer with aligned data
As a follow-up on Open-source vocal cloning (speech-to-speech neural style transfer), I want to create a voice clone. Unfortunately, the answers in the thread above do not apply to my language and ...
- 27
0
votes
0
answers
6
views
Example VQ-VAE code for audio in paper "Neural Discrete Representation Learning"
I want to replicate the paper "Neural Discrete Representation Learning" by van der Oord et al (2018). DeepMind provides an example for CIFAR images on GitHub.
It seems that the model for ...
- 27
2
votes
1
answer
98
views
Can we solve the environment with only the linear and angular position through Q-Learning?
I'm trying to solve the cartpole-v1 gym environment with only the linear and angular position, but the mean reward of the last 100 episodes isn't greater than 20 rewards. The longest train i made was ...
- 21
0
votes
0
answers
11
views
Masking during Instruction Tuning for LLM finetuning
I'm currently trying to learn more about LLMs particularly generative decoder only models such as the GPT family of models. I do have one question about masking though.
For me the way masking is ...
0
votes
1
answer
33
views
Methods of constructing input and ouput vectors in Reinforcement Learning with approximation function learning?
Give the one-hot state vector $\boldsymbol{x}(s)=[x_1(s),x_2(s)]^T$ and action spaces $A(s)=\{a_1,a_2\}$ for all $s$.
In a course, I was taught to construct "stack" input vectors like $[x_{...
0
votes
0
answers
73
views
Relating two small datasets, with Poisson, in a neural network or random network
I'm looking for a way to "relate" two small datasets, in Python, for predictive purposes. The two datasets are both independent and have no correlation (the numbers are randomly positioned). ...
- 101
0
votes
0
answers
8
views
extractive and generative q&a systems
I would like to build a q&a system because of the advancements in generative ai especially large language models (LLM) aka chatgpt and co. it seems like everyone wants to build this. So I started ...
- 175
0
votes
0
answers
21
views
cause and effect
I watched a tutorial video on AI. The author stated these:
1: "Any device that can perceive its environment and take action accordingly has AI."
2: "AI understands the cause and ...
- 101
0
votes
0
answers
19
views
How to let the AI trained on MNIST recognize my own hand-written number?
I have already trained a simple model without using any frameworks to recognize the hand-written numbers from the MNIST dataset. Actually it's just a copy of the example on the book Grokking ...
0
votes
0
answers
10
views
NaN gradients while Training (but loss isn't NaN neither the computational graph is disconnected)
The reason I am asking this here is that I haven't found a bug in my code and maybe there isn't a bug at all (or maybe there is). I just want to validate the idea that I am trying to implement. Here ...
- 101
0
votes
0
answers
5
views
Dimensions and file sizes of AI types (img/txt/sound) that work commercially and projections of future AI based on dimensionality and file simplicity?
Is it accurate that current AI breakthroughs are proportional to low dimensional complexity of datasets and small data throughput?
Image and text file renders are 100's of kilobytes, and they are ...
- 141
0
votes
1
answer
30
views
What are the techniques used to initialize weights for neural networks?
When creating a neural network to predict the impact of risks on the project cost, what techniques are used to initialize the weights provided to the hidden layers and the output layer?
- 11
1
vote
0
answers
14
views
Why slow-changing policy invalidates Double DQN approach in TD3 paper?
In the paper describing TD3 (https://arxiv.org/abs/1802.09477), the authors say that they could not effectively address the Q-learning overestimation bias by using different networks for maximizing ...
- 131
0
votes
0
answers
25
views
Is there a database of math conversations with Chat GPT?
I would like to make GPT (or other AI Chat, if someone knows better) to assist me in my mathematical education. But hard to say what GPT is capable to do. Some testing tasks are performed well by him, ...
- 101
0
votes
0
answers
13
views
Is Training Separate NER Models for Specific Labels a Viable Strategy for Improved Accuracy?
In my project, I'm utilizing Named Entity Recognition (NER) to identify crucial variables in prompts categorized into specific domains. However, incorporating numerous labels in the training data has ...
0
votes
1
answer
32
views
When are Transformers better than LSTMs in time-series tasks such as classification?
I’m working on a time-series classification problem and trying to decide whether to use a Transformer or an LSTM.
From what I’ve learned, Transformers are better suited for capturing long-range ...
2
votes
1
answer
425
views
Which epoch is the best for me to choose?
I have trained my deep learning model. I also saved the validation loss to a file and plotted on a graph
I have $2$ questions for this:
Does the validation loss look normal? Is there any issue with ...
user78437
0
votes
0
answers
13
views
i need dataset for human activity and diseases from smartphone accelerometer sensor?
project aims to develop a health monitoring system utilizing smartphone accelerometer sensors and machine learning techniques. The primary focus is on detecting specific health conditions through the ...
-1
votes
0
answers
18
views
LLM's for IMO-The 10m USD Problem
Just saw that Alex Gerko has launched a $10M challenge for the first AI to win IMO Gold. Link:https://aimoprize.com/
Curious, are there currently any viable LLM's that are even remotely good at ...
1
vote
1
answer
46
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 } ...
- 143
1
vote
1
answer
55
views
Types of activation functions used in neural networks
I need to specify the points and conditions that require me to use one activation function over another,
Why is it not possible to use the sigmoid FUNCTION in hidden layers, and it is preferable to ...
- 11
-2
votes
0
answers
18
views
how to address the rate limiting issue with ChatGPT-3.5? [closed]
ChatGPT has a rate limiting policy that restricts frequent access within a certain time period, resulting in denial of access. I would like to know how to overcome this issue and make multiple ...
- 1
0
votes
0
answers
9
views
Does the NEAT alogrithm disable genes randomly?
It is not mentioned in the original paper, if genes can be disabled randomly. They only mention that the connection gene is disabled, when a node is inserted in it's place. Is it the case, that genes ...
- 101
0
votes
1
answer
54
views
What is a "multinomial model" in machine learning?
What is the mathematical definition of "multinomial model" in machine learning?
I will be happy for a good definition plus an example.
- 492
-2
votes
0
answers
11
views
Can i integrate yolov5 with svm algorithm
I am currently working on an object detection project. I have already done it with yolov5 and svm separately can i integrate both the algorithm together like YOLO for object localization and detection ...
2
votes
1
answer
97
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
0
votes
0
answers
21
views
Using reinforcement learning to optimize a state-based potential function
I am using reinforcement learning for a project, and the objective function I want to optimize is a potential-based function. In other words, it is preferable for the agent to move to positions with ...
- 1
0
votes
0
answers
61
views
Why is chatGPT 4 unable to correct a program given its output?
Recently I used chatGPT 4 to write a small project in Perl which involved reading of an exam file (multiple choice), comparing it to a master exam file, and scoring the student exam including fraud ...
- 109
0
votes
0
answers
14
views
How to decide on how to define the output function for a neural network?
What I want my simple ML model to do is for a certain case file, to take the type of crime and the amount of damage(converted into dollars), and to make a judgment (in dollars incorporating price for ...
- 1
2
votes
0
answers
37
views
Why does only Deep Q Learning have an overestimation bias?
There is a lot of discussion about the overestimation bias for Deep Q Learning and similar off-policy action value estimation algorithms like DDPG. This is why methods like Double DQN and TD3 were ...
- 131
1
vote
0
answers
57
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
0
votes
0
answers
26
views
Is there serious game-theoretic work on AI risk and alignment?
My background is in political economy and game theory. I am interested in the discussion on AI risk and alignment, but I have so far failed to find work on this that seriously engages with classic ...
0
votes
2
answers
41
views
What does "Clustering features based on their values across objects rather than clustering objects ($X^T$ rather than$ X$)" mean?
In an ML book, it is said that:
"Similarly, clustering is a
popular choice for feature selection in classification-clustering features based on
their values across objects rather than clustering ...
- 492
0
votes
0
answers
23
views
Prefix tuning in LLM uses learnable vectors to fine tune the model
I would like to implement a new architecture for Transformer.
Below description is my thought.
Prefix tuning in LLM uses learnable vectors to fine tune the model.
Is there a way to use the output ...
- 9
1
vote
0
answers
40
views
Is AI good at detecting AI-generated content?
Are AI models good at detecting AI-generated image or video content like deep fakes? Which model can we use for the detection of AI-generated image content?
- 111
-1
votes
0
answers
11
views
Building ML model to identify latent line, shapes,forms [closed]
I am very new to ML and am wondering how it would be possible to train an ML program to identify latency to identify thing disguised or hidden beneath ( example) art works, coins, etc?
0
votes
1
answer
14
views
Retaining document level security of a CMS
I am responsible for a CMS that contains a lot of documents with knowledge and these documents are protected so not everyone can see them. Now we are tasked to find a technology partner who helps us &...
- 101
0
votes
1
answer
27
views
Is size of trained model on disk a good measure of model complexity?
I am writing a research paper on my own custom CNN model for image classification. I am comparing my model architecture with pre-trained architectures, like DenseNet121 and InceptionV3.
I want to ...
- 13
0
votes
0
answers
11
views
Could an analysis of GPT4's WAIS score be published?
Similar to this: https://www.scientificamerican.com/article/i-gave-chatgpt-an-iq-test-heres-what-i-discovered/
But more detailed and in depth (subtest breakdown, including image analysis, etc.), WAIS-...
- 113
1
vote
0
answers
24
views
cGAN: Discriminator loss going to zero while Generator's going always up but the result is very good
I have a Conditional Generative Adversarial Network for Quantum State Tomography. The metrics I am monitoring during the training process are the losses and the Fidelity (the degree of similarity ...
- 11
2
votes
0
answers
39
views
Is there a state-based approach to neural networks?
It occurred to me that neural networks operate like straight-line programs: an input is processed once by the layers, and an output is always immediately formed, in the same amount of time for each ...
- 121
1
vote
1
answer
52
views
Do GANs have constant running time?
After the model is trained, you just need to input random noise and the generator will output an image, does this mean GANs have constant running time ? I'm asking about both naïve GAN and variants of ...
- 61
0
votes
0
answers
35
views
Optimal decision with continuous, stochastic signals and rewards
I am performing a task, where I have to decide which projects to pursue at a given point in time, where the projects have different horizons of 30 minutes.
At a given point in time, forecasts are made ...
- 1
0
votes
0
answers
18
views
Can I use Prioritized Learning when the transition probabilities are given?
Can I use Prioritized Learning when the transition probabilities are given?
Also, as I can understand, Prioritized Sweeping is suitable when a state space is large. Can I use it when the state space ...
0
votes
1
answer
36
views
How LLM keeps the context of a chat/thread
How an LLM keeps the context (what has already been entered by the user) of a chat/thread?
For reference, in chat.openai.com, for each chat we create (or a Thread according to their API), the LLM ...
- 103
0
votes
0
answers
18
views
Also is there any way to create a gym environment that can be used without registering?
Please see the title: is there any way to create a gym environment that can be used without registering?
To be specific, since we have already created the environment class, is there any way to ...
- 21