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

Top Questions

1 vote
1 answer
82 views

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

0 votes
0 answers
2 views

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

1 vote
1 answer
37 views

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

1 vote
1 answer
67 views

How does backpropagation know which weights to change?

1 vote
1 answer
41 views

Why do Q-values diverge without a target network?

1 vote
1 answer
71 views

Hand-Signs Recognition using Deep Learning Convolutional Neural Networks

0 votes
0 answers
7 views

Data Imbalance in Contextual Bandit with Thompson Sampling

0 votes
0 answers
4 views

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

-1 votes
0 answers
6 views

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

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?

0 votes
0 answers
9 views

How does one detect training instabilities in DQN?

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?

1 vote
0 answers
7 views

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

14 votes
4 answers
2k views

Why are the initial weights of neural networks randomly initialised?

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?

4 votes
3 answers
361 views

Iteratively and adaptively increasing the network size during training

1 vote
1 answer
13 views

How to calculate the total number of inputs in CNN?

3 votes
2 answers
90 views

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

2 votes
1 answer
156 views

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

6 votes
4 answers
669 views

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

0 votes
0 answers
10 views

How does one define an "undefined" target?

2 votes
1 answer
19 views

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

2 votes
1 answer
122 views

Do smaller loss values during DQN training produce better policies?

0 votes
3 answers
106 views

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

0 votes
0 answers
11 views

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

0 votes
0 answers
8 views

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

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?

1 vote
1 answer
126 views

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

0 votes
0 answers
9 views

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

0 votes
1 answer
33 views

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

2 votes
1 answer
91 views

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

-2 votes
0 answers
11 views

is your database able to do research? [closed]

0 votes
1 answer
73 views

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

0 votes
0 answers
6 views

No question representation invlolved in the equation of a QA reader

0 votes
0 answers
6 views

In-batch negative training Improves the results

1 vote
0 answers
26 views

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

-2 votes
0 answers
19 views

Evaluation measure [closed]

-1 votes
0 answers
19 views

Before & After Discretization accuracy results [closed]

0 votes
1 answer
75 views

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

0 votes
0 answers
11 views

Application of Spectral analysis in NLP

0 votes
1 answer
48 views

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

0 votes
1 answer
26 views

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

0 votes
1 answer
30 views

Can off-policy algorithms benefit from the parallelization?

-1 votes
0 answers
10 views

Converting TensorFlow Keras model API to model subclassing [closed]

1 vote
0 answers
32 views

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

0 votes
1 answer
67 views

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

2 votes
1 answer
29 views

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

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?


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