Hottest Questions Today

1 vote

1 answer

43 views

Why do Q-values diverge without a target network?

Neil Slater

23.9k

modified 10 hours ago

1 vote

1 answer

13 views

How to calculate the total number of inputs in CNN?

convolutional-neural-networks classification image-processing weights

NikoNyrh

345

answered 19 hours ago

2 votes

1 answer

19 views

What are the possible ways to handle imbalance in multi-class image datasets?

deep-learning image-processing data-science imbalanced-datasets

hisairnessag3

1,155

answered 22 hours ago

0 votes

1 answer

33 views

How does the hidden activation differ from the output, at any time step for a SimpleRNN?

deep-learning recurrent-neural-networks

Kais Hasan

361

answered yesterday

0 votes

0 answers

11 views

Is there any literature on Span-Level Classification? [closed]

natural-language-processing reference-request architecture text-classification data-labelling

nbro

33.8k

modified yesterday

-2 votes

0 answers

11 views

is your database able to do research? [closed]

research human-like

Saiko obata

1

asked yesterday

4 votes

1 answer

142 views

Is plain autoencoder a generative model?

deep-learning autoencoders generative-model

Chillston

346

answered 2 days ago

0 votes

0 answers

11 views

Application of Spectral analysis in NLP

natural-language-processing python signal-processing

dato datuashvili

103

modified yesterday

0 votes

1 answer

26 views

How to interpret the output plan of the fast-downward planner

planning pddl strips

Bilal

105

modified yesterday

1 vote

0 answers

26 views

What is the most accurate way of building a Perceptron using only NumPy?

neural-networks python history perceptron numpy

Ghull

11

modified yesterday

0 votes

1 answer

58 views

+50

Why does mean episode reward during training differ dramatically from "manual" runs of the trained model on same data?

comparison deep-rl proximal-policy-optimization performance

Vladimir Belik

262

answered 12 hours ago

-2 votes

0 answers

19 views

Evaluation measure [closed]

testing

Gunners

11

modified yesterday

-1 votes

0 answers

19 views

Before & After Discretization accuracy results [closed]

accuracy discretization

Gunners

11

modified yesterday

-1 votes

0 answers

31 views

Error free learning for neural networks. What's the math behind it? [closed]

neural-networks machine-learning deep-learning c++

schwenk

99

modified 2 days ago

0 votes

1 answer

39 views

PPO vs SAC for discrete action spaces

reinforcement-learning comparison proximal-policy-optimization soft-actor-critic

nbro

33.8k

modified 2 days ago

0 votes

0 answers

33 views

What is the intuition about the fact that a set of images will live on a three dimensional manifold?

machine-learning image-processing curse-of-dimensionality

nbro

33.8k

modified 2 days ago

0 votes

1 answer

16 views

Where does the "rectified" in ReLU come from?

deep-learning terminology activation-functions relu

nbro

33.8k

modified 2 days ago

3 votes

1 answer

320 views

Is there a standardized method to train a reinforcement learning NN by demonstration?

neural-networks reinforcement-learning reference-request algorithm-request imitation-learning

nbro

33.8k

modified Jun 26 at 21:07

1 vote

0 answers

12 views

What inputs to give to a trained neural network?

neural-networks echo-state-network

nbro

33.8k

modified 2 days ago

2 votes

1 answer

29 views

How to tackle the human error made in labeling datasets for classification tasks like facial expression recognition?

neural-networks deep-learning facial-recognition clustering data-science

nbro

33.8k

modified 2 days ago

0 votes

0 answers

22 views

How to quickly train your agent to get a sense of the problem?

reinforcement-learning deep-rl dqn

goldfinch

13

modified Jun 28 at 20:18

0 votes

1 answer

29 views

How can I demonstrate a novel ML classification algorithm has value?

neural-networks machine-learning classification research

Arun Aniyan

96

answered 2 days ago

3 votes

1 answer

30 views

$E_{\pi}[R_{t+1}|S_t=s,A_t=a] = E[R_{t+1}|S_t=s,A_t=a]$?

reinforcement-learning markov-decision-process rewards sutton-barto expectation

DeepQZero

928

modified Jun 28 at 10:49

1 vote

0 answers

12 views

How do I preload a conversational AI assistant like GPT-3 with complex relational data to draw on?

natural-language-understanding gpt natural-language-generation gpt-3

Sam7

111

asked Jun 29 at 1:58

1 vote

1 answer

25 views

How to identify important features in data?

neural-networks convolutional-neural-networks long-short-term-memory deep-neural-networks

samuel fipps

11

answered Jun 28 at 23:29

0 votes

0 answers

14 views

How to Extract Specific Information From Web Pages Containing Job Postings?

natural-language-processing ai-design applications data-preprocessing implementation

nesquick

1

modified Jun 28 at 18:58

1 vote

1 answer

25 views

What consequence would a polynomial time algorithm for SAT have on AGI?

machine-learning agi computational-complexity

OmG

1,663

answered Jun 28 at 12:45

0 votes

1 answer

62 views

Why and when do we need to normalize weights in Reinforcement Learning?

reinforcement-learning weights weight-normalization

nbro

33.8k

modified 2 days ago

0 votes

1 answer

22 views

How do I know if my Random Forest Regressor Model is overfitted?

regression overfitting random-forests

Vladimir Belik

262

answered Jun 28 at 0:36

0 votes

0 answers

15 views

FastAi Image Classification [closed]

convolutional-neural-networks classification deep-neural-networks

Amitabha Chakraborty

1

asked Jun 28 at 12:05

-1 votes

0 answers

21 views

What is the most probable AI? [closed]

machine-learning deep-learning agi quantum-computing bayesian-statistics

Zeruel017

1

asked Jun 27 at 23:17

0 votes

2 answers

24 views

Why does the coding layer in a VAE have a range of values?

variational-autoencoder

Dr. Snoopy

566

answered Jun 26 at 20:58

1 vote

0 answers

25 views

Is it possible for AlphaGo Zero to use recurrent networks to achieve similar performance?

reinforcement-learning deep-rl recurrent-neural-networks alphago-zero alphago

nbro

33.8k

modified Jun 27 at 10:07

0 votes

0 answers

19 views

unable to calculate cross entropy loss due to shape of output and target in a transformer model [closed]

transformer loss cross-entropy

BOB

9

modified Jun 27 at 12:30

1 vote

1 answer

26 views

Does LSTM provide any unique value or advantages compared to other algorithms, including "vanilla" RNN?

deep-learning reference-request long-short-term-memory applications

nbro

33.8k

answered Jun 26 at 21:19

2 votes

0 answers

29 views

Today's Practicality of Bayesian Neural Networks

reference-request applications state-of-the-art bayesian-deep-learning bayesian-neural-networks

nbro

33.8k

modified 2 days ago

1 vote

2 answers

22 views

How to properly name given type of classification problem?

machine-learning deep-learning classification

nbro

33.8k

modified 2 days ago

-1 votes

0 answers

11 views

What are some SOTA conditional compute for inference papers? [closed]

convolutional-neural-networks inference

user3303020

99

asked Jun 27 at 19:10

0 votes

1 answer

20 views

How does a VAE sample the coding layer?

variational-autoencoder

nbro

33.8k

modified Jun 26 at 20:38

1 vote

0 answers

19 views

How to teach DRL agent to avoid erratic, high frequency behavior (when costs for taking actions are already included)?

deep-rl reward-design

Vladimir Belik

262

modified Jun 27 at 3:19

-1 votes

0 answers

11 views

Google AutoML Translation Advanced with Glossaries [closed]

google-translate automated-machine-learning google-cloud

Barış Akalın

1

asked Jun 27 at 13:22

0 votes

0 answers

11 views

Why do we subtract logsumexp from the outputs of this neural network?

neural-networks machine-learning loss mnist

nbro

33.8k

modified 2 days ago

0 votes

0 answers

19 views

What object detection algorithm is the best for my particular problem?

machine-learning object-detection algorithm-request yolo efficient-det

nbro

33.8k

modified 2 days ago

0 votes

1 answer

86 views

How do I create an AI controller for Pacman?

reinforcement-learning deep-learning deep-rl q-learning

Pluviophile

1,193

modified Jun 27 at 5:24

1 vote

0 answers

35 views

Do NNs suffer from lack of efficiency in network structure and suggesting training parameters?

neural-networks machine-learning optimization weights efficiency

Mehdi Moghadasian

11

modified Jun 26 at 12:36

2 votes

1 answer

70 views

What is being optimized with WGAN loss? Is the generator maximizing or minimizing the critic value?

generative-adversarial-networks loss wasserstein-gan

Gabriel Mongaras

21

modified Jun 25 at 3:48

3 votes

0 answers

23 views

How should I compare multiple machine learning models to be (generally) fair to all models?

machine-learning hyperparameter-optimization models

nbro

33.8k

modified Jun 26 at 9:29

1 vote

1 answer

19 views

Can the output layer be connected to multiple layers?

neural-networks machine-learning model-request

Chillston

346

answered Jun 26 at 12:05

Top Questions

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