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
Artificial Intelligence

Top Questions

Ask Question
Active 1 Bountied Hot Week Month
1 vote
1 answer
82 views

Why am I getting the logarithm of the probability bigger than zero when using Neural Spline Flows?

user avatar
CommunityBot
  • 1
0 votes
0 answers
2 views

Does maximizing the value funtion and maximizing the state-action value function generates the same optimal policy?

user avatar
Cloudy
  • 183
1 vote
1 answer
37 views

What is the appropriate RNN structure to do Sentiment Analysis with multiple dependent ratings?

user avatar
CommunityBot
  • 1
1 vote
1 answer
67 views

How does backpropagation know which weights to change?

user avatar
CommunityBot
  • 1
1 vote
1 answer
41 views

Why do Q-values diverge without a target network?

user avatar
Neil Slater
  • 23.9k
1 vote
1 answer
71 views

Hand-Signs Recognition using Deep Learning Convolutional Neural Networks

user avatar
CommunityBot
  • 1
0 votes
0 answers
7 views

Data Imbalance in Contextual Bandit with Thompson Sampling

user avatar
MABQ
  • 1
0 votes
0 answers
4 views

Why vector quantization won't work for higher bitrate for compression?

user avatar
Nervous Hero
  • 61
-1 votes
0 answers
6 views

(How can) I test my openai fine-tuned model against standard Question Answering benchmarks?

user avatar
samuelnihoul
  • 1
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?

user avatar
Vladimir Belik
  • 262
0 votes
0 answers
9 views

How does one detect training instabilities in DQN?

user avatar
desert_ranger
  • 287
0 votes
1 answer
51 views

YearPrediction dataset for a regression task: is it possible to evaluate a fair comparison between standard loss and a quadratic one?

user avatar
CommunityBot
  • 1
1 vote
0 answers
7 views

Neural network: Initial weights for layer with non-negative constraint

user avatar
Philipp123
  • 111
14 votes
4 answers
2k views

Why are the initial weights of neural networks randomly initialised?

user avatar
ksgr5566
  • 11
0 votes
0 answers
9 views

As someone starting out in RL, could you help me understand the differences between actor-only, critic-only, and actor-critic methods?

user avatar
No-Time-To-Day
  • 1
4 votes
3 answers
361 views

Iteratively and adaptively increasing the network size during training

user avatar
NikoNyrh
  • 345
1 vote
1 answer
13 views

How to calculate the total number of inputs in CNN?

user avatar
NikoNyrh
  • 345
3 votes
2 answers
90 views

Why some neural network models in the 1980s shown as circuit models

user avatar
dawen
  • 131
2 votes
1 answer
156 views

Use of virtual worlds (e.g. Second Life) for training Artificial General Intelligence agents?

user avatar
hisairnessag3
  • 1,155
6 votes
4 answers
669 views

Would it be ethical to allow an AI to make life-or-death medical decisions?

user avatar
Jay Mee
  • 1
0 votes
0 answers
10 views

How does one define an "undefined" target?

user avatar
Ryan
  • 3
2 votes
1 answer
19 views

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

user avatar
hisairnessag3
  • 1,155
2 votes
1 answer
122 views

Do smaller loss values during DQN training produce better policies?

user avatar
CommunityBot
  • 1
0 votes
3 answers
106 views

Is binary classification using CNN possible if the training data only consists of one class?

user avatar
CommunityBot
  • 1
0 votes
0 answers
11 views

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

user avatar
nbro
  • 33.8k
0 votes
0 answers
8 views

Is it possible to use a Support Vector Regression for continuous variables?

user avatar
nbro
  • 33.8k
2 votes
2 answers
79 views

How does one make a neural network learn the training data while also forcing it to represent some known structure?

user avatar
nbro
  • 33.8k
1 vote
1 answer
126 views

How to deal with Unix timestamps features of sequences, which will be classified with RNNs?

user avatar
nbro
  • 33.8k
0 votes
0 answers
9 views

Prototypical Network - Should I train my backbone or a separate embedder?

user avatar
nbro
  • 33.8k
0 votes
1 answer
33 views

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

user avatar
Kais Hasan
  • 361
2 votes
1 answer
91 views

What is the advantage of using experience replay (as opposed to feeding it sequential data)?

user avatar
desert_ranger
  • 287
-2 votes
0 answers
11 views

is your database able to do research? [closed]

user avatar
Saiko obata
  • 1
0 votes
1 answer
73 views

Which solutions are there to the problem of having too large activations before the softmax (or sigmoid) layer?

user avatar
CommunityBot
  • 1
0 votes
0 answers
6 views

No question representation invlolved in the equation of a QA reader

user avatar
Kais Hasan
  • 361
0 votes
0 answers
6 views

In-batch negative training Improves the results

user avatar
Kais Hasan
  • 361
1 vote
0 answers
26 views

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

user avatar
Ghull
  • 11
-2 votes
0 answers
19 views

Evaluation measure [closed]

user avatar
Gunners
  • 11
-1 votes
0 answers
19 views

Before & After Discretization accuracy results [closed]

user avatar
Gunners
  • 11
0 votes
1 answer
75 views

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

user avatar
PeterBe
  • 213
0 votes
0 answers
11 views

Application of Spectral analysis in NLP

user avatar
dato datuashvili
  • 103
0 votes
1 answer
48 views

Is there a way to improve the low-quality data?

user avatar
CommunityBot
  • 1
0 votes
1 answer
26 views

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

user avatar
Bilal
  • 105
0 votes
1 answer
30 views

Can off-policy algorithms benefit from the parallelization?

user avatar
Scrimbibete
  • 101
-1 votes
0 answers
10 views

Converting TensorFlow Keras model API to model subclassing [closed]

user avatar
Arun
  • 183
1 vote
0 answers
32 views

Why we need to do mutation after crossover? [duplicate]

user avatar
Mithical♦
  • 1,706
0 votes
1 answer
67 views

Train a model using a multi-column text-filled excel sheet

user avatar
CommunityBot
  • 1
2 votes
1 answer
29 views

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

user avatar
nbro
  • 33.8k
0 votes
0 answers
12 views

Is the interpretation of the "batch size" in policy gradient algorithms the number of trajectories sampled in VPG and TRPO?

user avatar
nbro
  • 33.8k

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

Your privacy

By clicking “Accept all cookies”, you agree Stack Exchange can store cookies on your device and disclose information in accordance with our Cookie Policy.