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

1 vote
1 answer
33 views

Is transfer learning effective when the new task has more classes than the original?

0 votes
0 answers
4 views

LSTM with time-series data transform

0 votes
0 answers
5 views

DDQN Snake keeps crashing into the wall

4 votes
1 answer
98 views

How can I encode angule data to train neural networks?

1 vote
1 answer
19 views

How can an ensemble be more accurate than the best base classifier in that ensemble?

0 votes
0 answers
25 views

My neural network does not appear to learn DQN

1 vote
1 answer
13 views

Gradient Accumulation VS Loss Accumulation

0 votes
0 answers
12 views

Alphago zero test phase

0 votes
1 answer
109 views

How does Weight Sharing with the Generalization in Graph Neural Networks work?

2 votes
2 answers
53 views

Why clip the PPO objective on only one side?

1 vote
0 answers
36 views

the connective conjunction and universal quantifier in sentences [migrated]

0 votes
0 answers
13 views

AI model to score potential candidates, as well as output a profile of the "ideal" candidate

0 votes
0 answers
2 views

What is the difference between prompt tuning and prefix tuning?

1 vote
1 answer
36 views

Can independent datasets be artificially combined for multimodal learning (semi-synthetic data generation)?

0 votes
2 answers
148 views

How to pass multiple vectors and numeric features as input to the neural network?

0 votes
0 answers
15 views

How can validation accuracy be more than test accuracy?

0 votes
2 answers
51 views

What should I do if my validation score is good, but my test score is bad?

2 votes
1 answer
209 views

How to implement RAM versions of Atari games

0 votes
0 answers
6 views

How are gradients backpropogated in ALBERT?

1 vote
2 answers
170 views

Can maximum likelihood be used as a classifier?

0 votes
0 answers
7 views

Keep weights of output layer in transfer learning?

0 votes
0 answers
7 views

What is $p(Z)$ and what happens to the variational posterior $q(Z;X)$ during data synthesis (after training)?

1 vote
2 answers
763 views

What is the relationship between the reward function and the value function?

0 votes
0 answers
17 views

ANN Input vector representing a network of contests's outcomes between thousands of individuals?

6 votes
2 answers
2k views

What is the difference between imitation learning and classification done by experts?

1 vote
1 answer
201 views

How can I identify bigrams and trigrams that represent concepts?

0 votes
0 answers
15 views

RNN: small weights

4 votes
1 answer
319 views

Why multiplayer, imperfect information, trick-taking card games are hard for AI?

1 vote
1 answer
48 views

Embedding Quality of Transfer Learning model vs Contrastive learning model

3 votes
1 answer
43 views

Is there a notion of location in Transformer architecture in subsequent self-attention layers?

1 vote
1 answer
48 views

What consequence would a polynomial time algorithm for SAT have on AGI?

1 vote
1 answer
28 views

Using TD algorithms, if the value function of terminal states is always 0, why would a policy ever choose it?

1 vote
0 answers
15 views

How do transformers compare to CNNs in terms of compute budget (and computing time) during inference?

0 votes
1 answer
49 views

In a DDQN architecture, why is the value of a state assumed to be the average of the Q values of the actions?

1 vote
2 answers
398 views

Why the cost/loss starts to increase for some iterations during the training phase?

0 votes
1 answer
41 views

What makes TRPO an Actor-critic method? Where is the critic?

0 votes
1 answer
29 views

Unsupervised pretraining on the supervised learning training data

0 votes
1 answer
498 views

Is there a performace benefits using VAE-GAN instead of just GAN?

0 votes
1 answer
58 views

Does a constant background in training data affect image classification model's performance?

-1 votes
0 answers
6 views

How to extract eyes vector from image through Style GAN?

4 votes
2 answers
51 views

How do I know how to design my ANN so that it fits my specific problem?

0 votes
0 answers
18 views

Reduce Variance for Reinforce Algorithm

1 vote
1 answer
38 views

Consider the following axioms-

0 votes
0 answers
14 views

FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models

1 vote
1 answer
106 views

What is meant by "spatial encoding" in the context of convolutional neural networks?

0 votes
1 answer
20 views

What does the figure in Q-learning vs Expected SARSA actually show?

0 votes
1 answer
38 views

Dummy variable trap in neural networks and class visualization

0 votes
1 answer
328 views

Does Value Loss in Actor Critic not decrease at all?


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