Hottest Questions This Month

5

votes

4

answers

3k

views

How can I predict the next number in a non-obvious sequence?

modified Oct 5 at 12:32 Peter Mortensen 141

4

votes

2

answers

664

views

Do we need automatic hyper-parameter tuning when we have a large enough dataset?

neural-networks hyperparameter-optimization training-datasets

modified Oct 17 at 20:51 nbro♦ 29.6k

1

vote

1

answer

92

views

What is a filter in the context of graph convolutional networks?

terminology papers convolution graph-neural-networks notation

modified 20 hours ago Eduardo Montesuma 96

5

votes

1

answer

99

views

How to decide a train-test split?

machine-learning training cross-validation testing

modified Oct 12 at 15:43 nbro♦ 29.6k

3

votes

2

answers

86

views

How does $\alpha$ affect the convergence of the TD algorithm?

reinforcement-learning reference-request convergence temporal-difference-methods learning-rate

modified Oct 23 at 11:23 nbro♦ 29.6k

4

votes

2

answers

79

views

Is it possible to tell the Reinforcement Learning agent some rules directly without any constraints?

reinforcement-learning

modified Oct 21 at 13:24 Pulse9 155

1

vote

1

answer

107

views

What exactly happens in gradient clipping by norm?

deep-learning pytorch gradient-clipping

modified Oct 10 at 8:10 nbro♦ 29.6k

2

votes

2

answers

88

views

In layman terms, what does "attention" do in a transformer?

neural-networks papers transformer attention

answered Oct 20 at 12:45 hH1sG0n3 121

3

votes

1

answer

63

views

How to determine the quality of synthetic data?

datasets autoencoders generative-model variational-autoencoder algorithm-request

answered Oct 12 at 19:44 ayandas 228

4

votes

2

answers

99

views

When to use Value Iteration vs. Policy Iteration

reinforcement-learning comparison q-learning value-functions policy-iteration

modified 2 days ago Shiyu 146

0

votes

1

answer

94

views

In this paper, if region $R_{2}$ moves in a sliding window manner, won't the saliency map have a smaller size than the original image?

computer-vision papers math convolution saliency-map

modified Oct 19 at 13:42 Archana David 256

1

vote

2

answers

73

views

What do people refer to when they use the word 'dimensionality' in the context of convolutional layer?

convolutional-neural-networks convolutional-layers 1d-convolution 2d-convolution 3d-convolution

modified Oct 9 at 0:00 nbro♦ 29.6k

3

votes

1

answer

63

views

What does "unknown search spaces" mean in the context of Evolutionary Algorithms?

terminology search evolutionary-algorithms neuroevolution

modified Oct 12 at 16:24 Commander 139

2

votes

1

answer

85

views

How do I choose the hyper-parameters for a model to detect different guitar chords?

convolutional-neural-networks object-detection hyperparameter-optimization convolution pooling

answered Oct 11 at 23:16 Archana David 256

2

votes

1

answer

51

views

What is the place of ontologies in artificial intelligence?

ai-design ontology knowledge-based-systems

modified 2 days ago nbro♦ 29.6k

0

votes

2

answers

50

views

Correctly input additional values into CNN

convolutional-neural-networks weights fully-connected-layer input-layer

answered Sep 29 at 14:02 John Rothman 63

1

vote

1

answer

37

views

Are there any animation tools available to visualise and simulate deep neural networks? [closed]

deep-learning deep-neural-networks models software-evaluation topology

modified Sep 30 at 0:55 DukeZhou♦ 6,246

1

vote

2

answers

46

views

When would it make sense to perform a gradient descent step for each term of a loss function with multiple terms?

deep-learning objective-functions mini-batch-gradient-descent

modified Oct 15 at 7:08 serali 917

0

votes

1

answer

58

views

Does the Weisfeiler-Lehman Isomorphism Test end?

graph-neural-networks graph-theory

modified Oct 22 at 9:25 user253751 387

1

vote

1

answer

44

views

What is the difference between gradient decent in neural networks and temporal difference in reinforcement learning?

neural-networks reinforcement-learning q-learning gradient-descent bellman-equations

modified Sep 29 at 14:22 nbro♦ 29.6k

3

votes

1

answer

40

views

What are the roles of the prior $\mathrm{p}(\mathbf{z})$ in a VAE?

generative-model variational-autoencoder

modified Oct 23 at 2:12 a12345 141

2

votes

1

answer

65

views

Closed networks vs Networks with a removed delay to predict new data

neural-networks comparison prediction feedforward-neural-network matlab

modified Oct 18 at 17:12 Archana David 256

0

votes

0

answers

62

views

+50

Understanding gumbel-softmax backpropagation in Wav2Vec papers

deep-learning papers audio-processing

modified yesterday Peter Franek 83

1

vote

1

answer

37

views

How are GCN doing semi-supervised learning?

papers graph-neural-networks semi-supervised-learning spectral-clustering

modified 22 hours ago nbro♦ 29.6k

1

vote

1

answer

61

views

PyTorch `torch.no_grad` vs `torch.inference_mode` [closed]

machine-learning pytorch gradient testing inference

answered Oct 13 at 16:50 efthimio 111

0

votes

1

answer

36

views

Does the ANN's training data include the proper output for every neuron?

neural-networks training backpropagation training-datasets

answered Oct 6 at 12:43 nbro♦ 29.6k

0

votes

1

answer

36

views

Probability that two words appear in the same sentence

natural-language-processing

modified Oct 15 at 19:49 Oliver Mason 4,756

1

vote

1

answer

28

views

What are the major layers in a Vision Transformer?

neural-networks deep-learning transformer layers vision-transformer

modified Oct 22 at 21:36 nbro♦ 29.6k

1

vote

1

answer

44

views

What is the name of the method for the smart extend of image surroundings?

reference-request image-processing image-generation image-inpainting image-outpainting

modified Oct 15 at 10:36 nbro♦ 29.6k

2

votes

1

answer

34

views

Is there any reason behind bias towards max pooling over avg pooling?

deep-learning pooling max-pooling pooling-layers average-pooling

modified Oct 18 at 20:28 nbro♦ 29.6k

1

vote

0

answers

53

views

Implementation of MDP in python to determine when to take action clean

python markov-decision-process markov-property

modified Oct 13 at 7:53 shan 111

2

votes

2

answers

32

views

Improving validation losses and accuracy for 3D CNN

neural-networks convolutional-neural-networks keras 3d-convolution

answered Oct 12 at 9:34 serali 917

1

vote

1

answer

32

views

Is there any recommended way to perform pooling in this context?

convolutional-neural-networks pytorch pooling

modified Oct 13 at 13:46 nbro♦ 29.6k

0

votes

1

answer

30

views

Is the noise term $\epsilon$ in $y=g(x) + \epsilon$ used to denote the model's imperfection to the real world?

supervised-learning noise

modified Sep 30 at 16:22 nbro♦ 29.6k

1

vote

0

answers

49

views

NEAT Speciation distance: How does one treat disabled connections?

neat

modified Oct 19 at 12:14 hanugm 2,219

0

votes

1

answer

38

views

Why is this vacuum cleaner agent rational?

intelligent-agent norvig-russell rationality rational-agents

modified Oct 19 at 12:30 nbro♦ 29.6k

1

vote

2

answers

29

views

How do the BFS and DFS search algorithms choose between nodes with the "same priority"?

search breadth-first-search depth-first-search

answered Oct 22 at 16:34 nbro♦ 29.6k

2

votes

1

answer

47

views

How to encourage the reinforcement-learning agent to reach the goal as quickly as possible, and what's the effect of discount factor?

reinforcement-learning deep-rl q-learning reward-functions discount-factor

modified Oct 8 at 12:58 nbro♦ 29.6k

2

votes

1

answer

36

views

Can RL still learn in a scenario where current state and the next state are independant?

machine-learning reinforcement-learning markov-decision-process

answered Oct 19 at 20:07 Neil Slater 20.6k

0

votes

0

answers

46

views

What algorithms minimize the log likelihood of sequential latent probabilistic models?

machine-learning algorithm-request pomdp latent-variable

modified 2 days ago nbro♦ 29.6k

0

votes

1

answer

43

views

Appropriate ML algorithm to solve a cutting pattern problem

machine-learning reinforcement-learning deep-rl ai-design ai-basics

answered Sep 30 at 9:22 Sanyou 158

1

vote

1

answer

33

views

Is there a benchmark for multi-objective evolutionary algorithms?

reference-request evolutionary-algorithms benchmarks moea nsga-2

modified Oct 16 at 23:40 nbro♦ 29.6k

0

votes

0

answers

42

views

how to get precision and recall from function 'precision_recall_curve' for class 0 [closed]

python

modified Oct 21 at 12:49 inquirer 3

0

votes

2

answers

32

views

In mini-batch gradient descent, do we pass each input in the batch individually or all inputs at the same time through the layer?

neural-networks deep-learning gradient-descent implementation mini-batch-gradient-descent

modified Sep 30 at 12:52 nbro♦ 29.6k

2

votes

1

answer

32

views

What can be an example for the prior knowledge used in Deep Learning systems?

deep-learning feature-engineering inductive-bias

modified Oct 8 at 12:20 nbro♦ 29.6k

0

votes

1

answer

31

views

Compare the efficiency of a trained ML model with a non-learning-based method for solving the same problem

neural-networks optimization metric algorithm-request efficiency

answered Oct 5 at 7:44 Edoardo Guerriero 1,658

1

vote

1

answer

24

views

Educational Resources and Programming Languages for AI & ML [closed]

machine-learning math linear-algebra

modified Oct 12 at 8:58 Commander 139

2

votes

1

answer

39

views

Does a bigger neural network learn "worse" representations than a small neural network when the amount of data isn't enough?

neural-networks deep-learning overfitting generalization feature-learning

modified Sep 28 at 14:01 nbro♦ 29.6k

Top Questions

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