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

8 votes
1 answer
1k views

What do symmetric weights mean and how does it make backpropagation biologically implausible?

3 votes
2 answers
45 views

Why doesn't the inception score measure intra-class diversity

2 votes
1 answer
147 views

Is it appropriate to represent 'total failure' as an absorbing state?

2 votes
1 answer
181 views

How does learning the moves of chess show up in a neural network?

4 votes
1 answer
59 views

Does the term "data augmentation" imply increasing the training dataset?

2 votes
1 answer
67 views

How to construct a reward function for a "wait and see" problem

1 vote
2 answers
49 views

Given a set of trajectories produced by a fixed policy, what is the the standard approach to estimate Q?

-1 votes
1 answer
102 views

can't find a viable import class for keras.utils.Sequence [closed]

1 vote
1 answer
46 views

What is the difference between features and inputs in machine learning?

0 votes
3 answers
74 views

How to deal with an unbalanced dataset?

-1 votes
1 answer
47 views

What is so special about the Bellman Optimality Principle?

-1 votes
1 answer
59 views

Denoise autoencoder not training properly [closed]

1 vote
0 answers
75 views

How are 4D cost volumes constructed for DL based stereo matching?

4 votes
1 answer
58 views

Why is it important/beneficial for an activation function to be zero-meaned?

0 votes
1 answer
54 views

Is there way to segment an image without labeling/classification, as well as supervised learning?

0 votes
2 answers
42 views

How to represent multi-label colours in one-hot encoding?

1 vote
1 answer
52 views

How should I write the reward function to teach the agent the rules of this card game?

1 vote
1 answer
40 views

What happens if all the features are correlated with each other before clustering?

3 votes
1 answer
40 views

What is the total number of actions and rewards count

1 vote
1 answer
47 views

Reinforcement learning algorithms for large problems that are not based on a neural network

3 votes
1 answer
36 views

What should the discount factor for the non-slippery version of the FrozenLake environment be?

2 votes
1 answer
45 views

Is it possible learning convergence is lost in Reinforcement Learning as the state space grows? What about catastrophic forgetting?

1 vote
1 answer
35 views

How to handled delayed rewards in contextual bandits [closed]

0 votes
1 answer
54 views

How can I reduce the loss? Why do I have the high loss and why do I have the gradient?

0 votes
1 answer
54 views

Why is depth-limited is preferable to minimax without depth limited

1 vote
1 answer
42 views

Is there some kind of "weighted maximum" that allows the gradients to backpropagate? [closed]

1 vote
1 answer
53 views

ML model to predict timeouts

2 votes
1 answer
32 views

What is a 'degenerate run' in evaluating model performance?

2 votes
0 answers
52 views

How to reduce the dimensionality of the actions in RL

0 votes
1 answer
40 views

How to understand the GCN equation?

0 votes
1 answer
51 views

Pattern recognition for live stream Time serie

0 votes
1 answer
50 views

Is there a term for unquantifiably uncertain prior knowledge?

1 vote
1 answer
38 views

Are there any guidelines on how to map the state space to integers in the case tabular RL algorithms?

1 vote
1 answer
29 views

Gradient bandit algorithm: is $\bar{R}_t$ average of all rewards or average of rewards corresponding to $A_t$?

1 vote
1 answer
36 views

Deep Features of Images - Better to use an unsupervised approach, or train a classifier with many classes?

0 votes
1 answer
35 views

BERT2: How to use GPT2LMHeadModel to start a sentence, not complete it

0 votes
1 answer
26 views

Is it possible to successively train an RL agent on the same environment with different data

0 votes
1 answer
33 views

Could Softmax Action Selection be useful to solve an episodic task with more than 100000 possible states and 2000 actions?

0 votes
0 answers
42 views

Which algorithm can find the best combination of players to maximize the chance of getting a high score?

0 votes
1 answer
32 views

How to manage impossible actions?

0 votes
0 answers
41 views

What is your training time of Resnet-18/Resnet-50 on Imagenet?

0 votes
0 answers
40 views

What is the correct partial derivative of $Y^c$ with respect to $A_{ij}^{kc}$?

0 votes
1 answer
31 views

How is policy iteration capable of improving on a deterministic policy?

2 votes
1 answer
24 views

Can we also estimate $V_{\pi}$ with SARSA?

1 vote
0 answers
39 views

Why do off-policy algorithms suffer from worse computational or time efficiency compared to on-policy algorithms?

1 vote
0 answers
39 views

Learning values in open ball: which final layers to employ?

1 vote
0 answers
38 views

Why does the SVM perform poorly on test data that has a different class distribution than the training data?

1 vote
1 answer
38 views

Can you make a Neural Network drunk or high?


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