Skip to main content

Top Questions

3 votes
1 answer
179 views

Can we implement a memory in a REINFORCE algorithm for RL?

1 vote
1 answer
70 views

What is the formula for $VC(H)$ in Computational Learning Theory? [duplicate]

1 vote
2 answers
65 views

tic-tac-toe - tabular q-learning - what is the formula to calculate the number of entries in the q-table

1 vote
1 answer
52 views

Why do we need complex neural network designs?

-1 votes
1 answer
57 views

Can anyone please explain the Recurrent Neural Network calculation shown in the picture?

0 votes
1 answer
57 views

What are disadvantages/limitations of Monte Carlo Tree Search in RL?

0 votes
1 answer
72 views

Is reinforcement learning suitable for application automation?

-1 votes
1 answer
70 views

Violation of Markov property

1 vote
2 answers
53 views

Can transformer attention make predictions based on analogy?

2 votes
1 answer
51 views

Will an AI LLM learn a language if fed during training with a large corpus of undeciphered language?

1 vote
3 answers
37 views

How is it possible that RAG embeddings implemented with a different embedding model than the pre-trained LLM can work?

0 votes
1 answer
61 views

How to evaluate the relevance of a search made with an AI Agent?

2 votes
1 answer
59 views

Why fine tuning does not work as well as RAG?

2 votes
1 answer
54 views

Are there LLMs that are allowed time to contemplate freely?

0 votes
1 answer
42 views

Does the off-policy/on-policy regime plays role in Contextual Bandits?

0 votes
0 answers
52 views

I can’t pass a treshold no matter what I do

0 votes
0 answers
51 views

Proof of gradient of $v_{\pi}(s)$ via Kronecker Product

0 votes
1 answer
39 views

Confusing statement in Sutton-Barto on trajectory sampling

2 votes
1 answer
39 views

Should the experience replay memory only contain unique experiences?

0 votes
2 answers
49 views

What do we mean by "AI is correlated"?

1 vote
0 answers
48 views

AI capable of mathematical creation? (reference request)

0 votes
1 answer
36 views

Are there problems where the optimal policy is stochastic?

0 votes
1 answer
36 views

Why are the Q and K matrices two separate matrices in attention?

-2 votes
1 answer
28 views

Unclear line in prioritized sweeping algorithm [closed]

0 votes
1 answer
35 views

How do neural-network chess engines select moves?

0 votes
1 answer
35 views

Does 1-bit quantization (layers with boolean tensors) machine learning exist?

0 votes
1 answer
34 views

Dot notation for matrix element index in formula of word2vec embedding calculation

0 votes
1 answer
26 views

Sparse Cross Entropy

1 vote
0 answers
42 views

Obtaining canonical example sentences from an embedding

1 vote
0 answers
40 views

Why is policy gradient theorem so important?

-1 votes
0 answers
39 views

Is there any offline AI solution integrated with OS? [closed]

0 votes
1 answer
30 views

Can a neral network learn dependencies that can be expressed only by iterative approaches

0 votes
1 answer
38 views

Why Tokenization Algorithm replace space with underscore "_"?

-1 votes
1 answer
29 views

Creating a replacement for backpropagation through evolution [closed]

1 vote
0 answers
37 views

Why doesn't the Kolmogorov-Arnold representation theorem imply an MLP-like structure?

0 votes
0 answers
36 views

Good and free resources to learn about AI ML as a beginner (if possible, then do not suggest books)

0 votes
1 answer
21 views

How would I approach finding the source code for the paper that is being discussed in this article?

1 vote
1 answer
26 views

Can you claim copyright over a social media post that is used to train an AI model?

0 votes
0 answers
33 views

What are the update equations for Double Expected Sarsa with an $\epsilon$-greedy target policy?

0 votes
1 answer
33 views

Is sparsity required for behaviour exhibited by modular neural networks such as compositional generalisation, resiliency to catastrophic learning?

-1 votes
1 answer
33 views

Pytorch Encoder not working [closed]

0 votes
1 answer
25 views

The format of data for text generation using LLM

0 votes
0 answers
32 views

Back-propagation through embedding layer

0 votes
2 answers
24 views

How does the Clustering algorithm comes up with the name for each cluster?

0 votes
0 answers
30 views

Structure and parameters of modern AI-baed chess engines

0 votes
1 answer
30 views

How do I improve the prediction speed of a model?

0 votes
1 answer
30 views

Why does LoRA has encoder-decoder structure?

0 votes
1 answer
23 views

Determining optimal data size for generalization in transformer encoders, particularly for Time-Series signal data


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