Artificial Intelligence Stack Exchange

1

vote

1

answer

4

views

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

modified 1 min ago nbro♦ 13.9k

0

votes

0

answers

3

views

Do I have to crossover my node genes in NEAT, and how?

neat crossover mutation

asked 51 mins ago Dara Kong 1

0

votes

1

answer

6

views

Does this prove AI Safety is undecidable?

agi ai-safety

modified 57 mins ago nbro♦ 13.9k

0

votes

0

answers

6

views

AI predicting on what's going to Happen through Gaming?

machine-learning game-ai

asked 1 hour ago thegamerguy 1

0

votes

0

answers

7

views

Should I be trying to create a generic application or something more specific to a particular game?

reinforcement-learning game-ai learning-algorithms

modified 2 hours ago mason7663 239

0

votes

1

answer

90

views

Why is it ok to calculate the reward based on a hidden state?

reinforcement-learning rewards

modified 2 hours ago nbro♦ 13.9k

1

vote

0

answers

6

views

How should I define the reward function for the Connect Four game?

reinforcement-learning ai-design markov-decision-process rewards

modified 2 hours ago mason7663 239

1

vote

0

answers

8

views

Is the TD-residual defined for timesteps $t$ past the length of the episode?

reinforcement-learning policy-gradients temporal-difference

modified 2 hours ago bxw 33

1

vote

0

answers

8

views

Why can the core reinforcement learning algorithms be applied to POMDPs?

reinforcement-learning markov-decision-process pomdp

modified 3 hours ago nbro♦ 13.9k

2

votes

2

answers

14

views

Why is there an expectation sign in the Bellman equation?

reinforcement-learning value-function expectation bellman-equations

modified 3 hours ago nbro♦ 13.9k

6

votes

1

answer

170

views

Why do Bellman equations indirectly create a policy?

reinforcement-learning comparison policy-gradients bellman-equations

modified 3 hours ago nbro♦ 13.9k

0

votes

0

answers

7

views

More Relevant and Compact Learning Material For Artificial Intelligence [closed]

neural-networks machine-learning deep-learning research

asked 3 hours ago Muhammad Usman 101

9

votes

1

answer

2k

views

What is the Bellman operator in reinforcement learning?

reinforcement-learning terminology math

modified 3 hours ago nbro♦ 13.9k

2

votes

1

answer

91

views

Why is this ResNet50 misclassifying objects?

machine-learning deep-learning classification image-recognition keras

modified 4 hours ago Community♦ 1

1

vote

1

answer

23

views

Which humanoid robots have open-source software (or hardware)?

reference-request robotics resource-request robots humanoid-robots

modified 4 hours ago tynowell 131

2

votes

0

answers

36

views

Does Rice's theorem prove safe AI is undecidable?

agi proofs ai-safety theory-of-computation

modified 4 hours ago nbro♦ 13.9k

1

vote

0

answers

12

views

How can I find the appropriate reward value for my reinforcement learning problem?

reinforcement-learning ai-design rewards

modified 5 hours ago nbro♦ 13.9k

1

vote

1

answer

20

views

What is the role of convex optimisation in AI systems?

machine-learning optimization

modified 7 hours ago nbro♦ 13.9k

1

vote

1

answer

21

views

Should I always start from the same start state in reinforcement learning?

reinforcement-learning training gym

answered 7 hours ago Edoardo Guerriero 336

0

votes

2

answers

23

views

How can I train a neural network if I don't have enough data?

neural-networks backpropagation optimization matlab

answered 7 hours ago Paul Higazi 46

7

votes

3

answers

384

views

What types of applications qualify as “compound intelligences”?

machine-learning definitions applications reference-request swarm-intelligence

modified 7 hours ago nbro♦ 13.9k

1

vote

1

answer

17

views

Data scan not making sense for coco dataset

training yolo loss

modified 8 hours ago Community♦ 1

1

vote

0

answers

12

views

What are the most common non-Markov RL paradigms?

reinforcement-learning markov-decision-process markov-property

modified 8 hours ago Stan Shunpike 111

1

vote

0

answers

17

views

Is the derivative of the loss wrt a single scalar parameter proportional to the loss?

machine-learning deep-learning math proofs

modified 9 hours ago Zyuuu 11

3

votes

1

answer

33

views

Do all expert trajectories have the same starting state in apprenticeship learning?

reinforcement-learning papers rewards apprenticeship-learning

modified 9 hours ago calveeen 407

1

vote

0

answers

19

views

NN for card game evaluation function

neural-networks convolutional-neural-networks keras game-ai

modified 10 hours ago Cyrus Dobbs 21

1

vote

1

answer

33

views

How can I merge outputs of two separate layers so that the overall performance improves?

deep-learning convolutional-neural-networks keras performance

modified 10 hours ago nbro♦ 13.9k

1

vote

1

answer

24

views

Alternatives to U-Net for biomedical image segmentation

neural-networks deep-learning convolutional-neural-networks image-segmentation

answered 11 hours ago Paul Higazi 46

0

votes

0

answers

13

views

How can I implement a Facial Recognition algorithm in C++ from scratch, without using OpenCV?

machine-learning ai-design classification training ai-basics

asked 12 hours ago Ana Gheorghiță 1

1

vote

0

answers

11

views

Efficient algorithm to obtain near optimal policies for an MDP

reinforcement-learning markov-decision-process

asked 13 hours ago ijuneja 121

1

vote

0

answers

6

views

How to generate non-linear line connection by using Taylor series for CNN like model in python?

deep-learning convolutional-neural-networks keras image-recognition

asked 18 hours ago Dan 111

-2

votes

0

answers

43

views

a simple new way to artificial intelligence [closed]

ai-basics

modified 18 hours ago Mendez north 1

1

vote

1

answer

156

views

How to encode card game state into neural network input

neural-networks game-ai

modified 20 hours ago Community♦ 1

0

votes

0

answers

24

views

What is the difference between using dense layers vs convolutional layers when dealing with images/image data?

neural-networks convolutional-neural-networks comparison generative-adversarial-networks

modified 22 hours ago nbro♦ 13.9k

3

votes

2

answers

40

views

Can a data compression function be used to make predictions?

ai-design agi prediction

answered 22 hours ago nbro♦ 13.9k

2

votes

1

answer

76

views

What assumptions are made when positing the emergence of superintelligence?

philosophy agi superintelligence

modified 22 hours ago nbro♦ 13.9k

3

votes

1

answer

202

views

What are the AI technologies currently used to fight the coronavirus pandemic?

modified 22 hours ago nbro♦ 13.9k

1

vote

1

answer

38

views

What is relation between gradient descent and regularization in deep learning?

deep-learning comparison gradient-descent regularization hyper-parameters

modified yesterday DuttaA 4,427

0

votes

1

answer

50

views

Is my backpropagation code correct? [closed]

neural-networks algorithm backpropagation matlab sigmoid

modified yesterday nbro♦ 13.9k

1

vote

2

answers

82

views

TensorFlow 2.0 - Normalizing input to DNN (on structured data)

neural-networks deep-learning tensorflow datasets

modified yesterday Community♦ 1

1

vote

1

answer

24

views

How to calculate the confidence of a classifier's output?

classification

modified yesterday Community♦ 1

2

votes

1

answer

71

views

Which deep reinforcement learning algorithm is appropriate for my problem?

reinforcement-learning optimization deep-rl

modified yesterday Joel Joseph 13

0

votes

1

answer

31

views

The Nature of Model Weights for Targeted Dropout

artificial-neuron sequence-modelling

modified yesterday Community♦ 1

0

votes

0

answers

7

views

tf.data.Dataset: The `batch_size` argument must not be specified for the given input type [migrated]

neural-networks deep-learning tensorflow keras google-cloud

asked yesterday Sami Belkacem 1

0

votes

0

answers

6

views

What are the current research trends in recognizing narrative similarity?

machine-learning natural-language-processing natural-language-understanding

asked yesterday JavaApprentice 11

1

vote

1

answer

87

views

Which model can I use for this problem with multiple inputs and outputs?

ai-design tensorflow keras prediction

modified yesterday Community♦ 1

0

votes

0

answers

9

views

How to productionize a YOLO model? [migrated]

image-processing yolo inference

modified yesterday nbro♦ 13.9k

0

votes

0

answers

15

views

How should I define the loss function when using DQN to estimate the probability density?

reinforcement-learning loss-functions dqn deep-rl

modified yesterday nbro♦ 13.9k

Top Questions

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