Artificial Intelligence Stack Exchange

0

votes

0

answers

2

views

Is it possible to create intelligence with metaprogramming?

artificial-neuron programming-languages computer-programming artificial-life

asked 46 mins ago Dimer 45

5

votes

2

answers

1k

views

Why L1/L2 regularization technique did not improve my accuracy?

neural-networks deep-learning training overfitting regularization

answered 3 hours ago MrStutterZ 1

0

votes

0

answers

9

views

Is there a rule-of-thumb to determine which behaviours must be learned in a lifetime and which innate?

neural-networks evolutionary-algorithms

modified 3 hours ago nbro 5,478

0

votes

0

answers

5

views

When should I stop the object detection model training while mAP are not stable?

deep-learning computer-vision tensorflow object-detection

asked 4 hours ago lllllllllllll 139

1

vote

1

answer

9

views

Why are activation functions independent layers in CNNs rather than part of convolutional layers?

neural-networks convolutional-neural-networks definitions activation-function mlp

modified 4 hours ago nbro 5,478

0

votes

0

answers

22

views

Unique game problem (ML, DP, PP etc)

machine-learning reinforcement-learning game-ai q-learning probability

modified 4 hours ago rambossa 101

1

vote

0

answers

19

views

What is ratio of the objective function in the case of continuous action spaces?

reinforcement-learning ai-design proximal-policy-optimization

modified 5 hours ago nbro 5,478

0

votes

1

answer

16

views

Can HMM, MRF, or CRF be used to classify the state of a single observation, not the entire observation sequence?

markov-chain sequence-modelling time-series hidden-markov-model

modified 6 hours ago Community♦ 1

2

votes

2

answers

37

views

Which online machine learning technique to use for multi-class classification problem with multiple inputs?

machine-learning ai-design classification mlp online-learning

answered 7 hours ago nbro 5,478

1

vote

2

answers

17

views

Are feature maps merged or are they passed on as they are?

neural-networks deep-learning convolutional-neural-networks definitions implementation

answered 9 hours ago Djib2011 346

1

vote

1

answer

42

views

Way to control movement and coverage in an embedded AI cleaning system?

machine-learning optimization embedded-design

modified 10 hours ago Community♦ 1

0

votes

1

answer

33

views

If the goal of training of a GAN is to have $P_g=P_{data}$, shouldn't this produce the exact same images?

deep-learning convolutional-neural-networks generative-adversarial-networks generative-model image-generation

modified 11 hours ago nbro 5,478

-2

votes

1

answer

44

views

Problem over DQN Algorithm not converging on snake

reinforcement-learning python tensorflow q-learning dqn

modified 12 hours ago Raphe 1

2

votes

1

answer

22

views

Will the target network, which is less trained than the normal network, output inferior estimates?

reinforcement-learning q-learning dqn deep-rl

modified 13 hours ago nbro 5,478

Stack Exchange Network

current community

your communities

more stack exchange communities

Explore Our Questions

Is it possible to create intelligence with metaprogramming?

Why L1/L2 regularization technique did not improve my accuracy?

Is there a rule-of-thumb to determine which behaviours must be learned in a lifetime and which innate?

When should I stop the object detection model training while mAP are not stable?

Why are activation functions independent layers in CNNs rather than part of convolutional layers?

Unique game problem (ML, DP, PP etc)

What is ratio of the objective function in the case of continuous action spaces?

Can HMM, MRF, or CRF be used to classify the state of a single observation, not the entire observation sequence?

Which online machine learning technique to use for multi-class classification problem with multiple inputs?

Are feature maps merged or are they passed on as they are?

Way to control movement and coverage in an embedded AI cleaning system?

If the goal of training of a GAN is to have $P_g=P_{data}$, shouldn't this produce the exact same images?

Problem over DQN Algorithm not converging on snake

Will the target network, which is less trained than the normal network, output inferior estimates?

Hot Network Questions