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
20 views

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

5 votes
1 answer
123 views

How can I encode angule data to train neural networks?

0 votes
0 answers
28 views

My neural network does not appear to learn DQN

0 votes
0 answers
15 views

Alphago zero test phase

1 vote
1 answer
14 views

Gradient Accumulation VS Loss Accumulation

1 vote
1 answer
35 views

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

1 vote
0 answers
37 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
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?

0 votes
0 answers
17 views

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

0 votes
0 answers
15 views

RNN: small weights

1 vote
1 answer
29 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
29 views

Unsupervised pretraining on the supervised learning training data

1 vote
1 answer
36 views

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

0 votes
1 answer
20 views

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

3 votes
2 answers
64 views

What is the definition of a continuous state/action space?

1 vote
1 answer
45 views

What is the intuition behind self-attention?

0 votes
0 answers
18 views

Reduce Variance for Reinforce Algorithm

0 votes
0 answers
14 views

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

0 votes
1 answer
86 views

I’m making a simple neural network from scratch and it won’t learn anything. Please help [closed]

0 votes
0 answers
23 views

Inferring a transition model from incomplete data subject to rules

2 votes
2 answers
42 views

Back propagation activation function derivative [closed]

4 votes
2 answers
51 views

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

2 votes
1 answer
23 views

Did old-fashioned, rule-based systems die out when statistical learning broke through into NLP?

15 votes
2 answers
1k views

Are softmax outputs of classifiers true probabilities?

0 votes
0 answers
13 views

Value Of Trees In Decision Tree

1 vote
1 answer
16 views

Train Deep Q-Learning Network on a game without source code

0 votes
1 answer
21 views

symbolic gradient vs automatic differentiation

0 votes
0 answers
23 views

Can models really get smarter the more you use them?

2 votes
1 answer
51 views

Why do activation functions in neural networks have to be non-polynomial to approximate any function?

0 votes
0 answers
30 views

What is the theory behind rejecting too good heuristics in search problems?

0 votes
0 answers
15 views

Leaky hard sigmoid activation function

1 vote
1 answer
38 views

Find maxima and minima of feed forward neural network given interval inputs [closed]

0 votes
0 answers
19 views

Embedding layers/entities in openAI's Hide and seek paper

0 votes
0 answers
16 views

The episode length increases at the start till it reaches a peak then decreases. What can cause this unexpected behavior?

1 vote
1 answer
38 views

Consider the following axioms-

0 votes
0 answers
13 views

Is it redunant to add more layers to a neural network with same number of neurons as the previous layer?

0 votes
1 answer
21 views

How do we combine feature maps? CNN

0 votes
1 answer
15 views

Is it possible to perform node-level classification and graph-level classification on the same graph?

2 votes
1 answer
42 views

Are the "artifacts" in select Keras MNIST training images really there or is my download corrupt?

1 vote
0 answers
16 views

Intelligent Agents with Personality - Implementation

0 votes
0 answers
11 views

About the Evaluation method of the Market 1501 ReID dataset

0 votes
0 answers
18 views

How does counterfactual regret minimization updates strategy when the agent is consecutive? [closed]

1 vote
0 answers
16 views

Where does the proximal policy optimization objective's ratio term come from?

0 votes
0 answers
12 views

detectron2 draws a segmentation mask for the "unlabeled" semantic category [closed]

0 votes
0 answers
33 views

How does the discount factor (gamma) and memory replay work in Deep Q-learning?


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