Artificial Intelligence Stack Exchange is a question and answer site for people interested in conceptual questions about life and challenges in a world where "cognitive" functions can be mimicked in purely digital environment. It only takes a minute to sign up.

Sign up to join this community
Anybody can ask a question
Anybody can answer
The best answers are voted up and rise to the top

Top Questions

2 votes
2 answers
21 views

Why LLMs land RNNs earn so fast during inference but, ironically, so slow during training?

0 votes
0 answers
4 views

Redundancy of Value-Projection-matrix in Multi-headed attention in Transformer model

2 votes
2 answers
88 views

How the proof of the contraction of variance for distributional Bellman operator follows

0 votes
0 answers
5 views

Network is not learning for computation of eigenvalue and eigenvector problem

2 votes
1 answer
22 views

relu and gradient descent

0 votes
2 answers
33 views

Is manual binding output to input also an AI?

0 votes
1 answer
479 views

In-batch negative training Improves the results

1 vote
1 answer
86 views

Is the multi-head attention in the transformer a weighted adjacency matrix?

0 votes
2 answers
126 views

Is google able to recognize Chat GPT content?

0 votes
1 answer
37 views

How do you pass from the 192 depth in the first tensor to the 256 in the second tensor?

0 votes
0 answers
6 views

Training two DQNs at the same time: one for task allocation, the other for action selection

1 vote
2 answers
42 views

Does MSE loss function work in NN training for predicting values between 0-1?

0 votes
2 answers
91 views

Converting RGB images to Thermal Images

0 votes
0 answers
17 views

How do I obtain a feature map of an arbitrarily size during atrous convolution? (DeepLab V2)

0 votes
0 answers
9 views

Denoising auto encoder for 2D signals

0 votes
0 answers
8 views

Position embeddings in Vision Transformer

0 votes
0 answers
7 views

Do deep ensembles and regular ensembles coincide for classification tasks?

0 votes
0 answers
11 views

How does Knowledge Distillation help Federated Learning?

0 votes
0 answers
15 views

How to extract product codes within unstructured data

0 votes
0 answers
9 views

How do I train a DQN agent against an ai for an asymmetric game

0 votes
1 answer
13 views

using bitmaps for storing and analyzing numeric data (use case: flight sim game AI)

2 votes
1 answer
460 views

Can we use a pre trained Encoder (BERT, XLM ) with a Decoder (GPT, Transformer-XL) to build a Chatbot instead of Language Translation?

1 vote
0 answers
25 views

LLM-like architecture capable of dynamically learning from its own output

3 votes
3 answers
419 views

If I trained a model to perform semantic segmentation on images with only one object, would it also work on images with multiple objects?

1 vote
2 answers
100 views

Why does Q-function training not query the Q-function value at unobserved states?

0 votes
1 answer
499 views

KL divergence coefficient update doesn't make sense in RLlib's PPO implementation

0 votes
1 answer
37 views

Recognize patterns within random sequences

0 votes
0 answers
16 views

Meaning of roles in the API of GPT-4/ChatGPT (system/user/assistant)

2 votes
1 answer
216 views

How to represent integer values in sequence to sequence prediction task in encoder-decoder LSTM?

1 vote
1 answer
220 views

Dropout causes too much noise for network to train

3 votes
1 answer
145 views

How do I poison an SVM with manifold regularization?

0 votes
1 answer
45 views

Which meta-learning approach selection methodology should I use for similarity learning of an image?

0 votes
0 answers
14 views

What metrics are there to measure the similarity of two disjoint sets of points?

2 votes
1 answer
278 views

How could Bayesian neural networks be used for transfer learning?

0 votes
0 answers
25 views

Creating or using a corpus for a chatbot interaction modelling for an existing intelligent tutor system

3 votes
0 answers
17 views

Why does training converges when the norm of gradient increases?

1 vote
0 answers
18 views

What else beyond convnets is needed to detect sameness in a Bongard problem?

1 vote
1 answer
100 views

What temperature would you recommend for the chatgpt api?

0 votes
0 answers
25 views

Detecting deepfake video

0 votes
0 answers
13 views

Clustering by number of spacial nodes in an area

0 votes
0 answers
21 views

Can I reduce computation by only predicting response tokens in a transformer and still get the same gradients?

2 votes
1 answer
675 views

Binary mode or Multi-label mode is correct when using binary crossentropy and sigmoid output function on multi-label classification

0 votes
0 answers
10 views

Is it possible to apply entity fixed effects to a firth logit test?

2 votes
2 answers
206 views

Is the output of image generation models like Midjourney and Stable Diffusion deterministic?

0 votes
0 answers
26 views

How does a LLM (specifically transformer) pick words from it's vocabulary?

1 vote
1 answer
97 views

Can the law of iterated expectation be used on the inner expectation of the DQN cost function described in the DQN paper

2 votes
2 answers
56 views

Are any AI systems available, or in development, for finding and analysing fallacious inference in natural language text?

0 votes
1 answer
51 views

What should I do, reinforcement learning agent gives different result on every train?


Looking for more? Browse the complete list of questions, or popular tags. Help us answer unanswered questions.