1 | What is "backprop"? | What does "backprop" mean? Is the "backprop" term basically the same as "backpropagation" or does it have a different meaning? | 2016-08-02T15:39:14.947 | 10 | 659 | <neural-networks><backpropagation><terminology><definitions> |
2 | How does noise affect generalization? | Does increasing the noise in data help to improve the learning ability of a network? Does it make any difference or does it depend on the problem being solved? How is it affect the generalization process overall? | 2016-08-02T15:40:20.623 | 14 | 897 | <neural-networks><machine-learning><statistical-ai><generalization> |
3 | nan | "Backprop" is the same as "backpropagation": it's just a shorter way to say it. It is sometimes abbreviated as "BP". | 2016-08-02T15:40:24.820 | 15 | 0 | nan |
4 | How to find the optimal number of neurons per layer? | When you're writing your algorithm, how do you know how many neurons you need per single layer? Are there any methods for finding the optimal number of them, or is it a rule of thumb? | 2016-08-02T15:41:22.020 | 33 | 1172 | <neural-networks><hyperparameter-optimization><artificial-neuron><hyper-parameters><layers> |
6 | Are humans intelligent according to the definition of an intelligent agent? | Given the following definition of an intelligent agent (taken from a Wikipedia article) If an agent acts so as to maximize the expected value of a performance measure based on past experience and knowledge then it is intelligentand given that we, humans, all make mistakes, which means that we are n… | 2016-08-02T15:43:35.460 | 7 | 269 | <philosophy><definitions><intelligent-agent> |
7 | Why does Stephen Hawking say "Artificial Intelligence will kill us all"? | This quote by Stephen Hawking has been in headlines for quite some time:Artificial Intelligence could wipe out humanity when it gets too clever as humans will be like ants.Why does he say this? To put it simply: what are the possible threats from AI (that Stephen Hawking is worried about)? If we kno… | 2016-08-02T15:45:09.070 | 10 | 567 | <agi><superintelligence><singularity><ai-safety><ai-takeover> |
9 | nan | Noise in the data, to a reasonable amount, may help the network to generalize better. Sometimes, it has the opposite effect. It partly depends on the kind of noise ("true" vs. artificial).The AI FAQ on ANN gives a good overview. Excerpt: Noise in the actual data is never a good thing, since it limi… | 2016-08-02T15:47:02.993 | 9 | 0 | nan |
10 | What is fuzzy logic? | I'm new to A.I. and I'd like to know in simple words, what is the fuzzy logic concept? How does it help, and when is it used? | 2016-08-02T15:47:56.593 | 50 | 2460 | <deep-neural-networks><terminology><fuzzy-logic> |
11 | nan | We typically think of machine learning models as modeling two different parts of the training data--the underlying generalizable truth (the signal), and the randomness specific to that dataset (the noise).Fitting both of those parts increases training set accuracy, but fitting the signal also increa… | 2016-08-02T15:48:56.970 | 9 | 0 | nan |
12 | nan | There is no direct way to find the optimal number of them: people empirically try and see (e.g., using cross-validation). The most common search techniques are random, manual, and grid searches. There exist more advanced techniques such as Gaussian processes, e.g. Optimizing Neural Network Hyperpara… | 2016-08-02T15:50:27.867 | 19 | 0 | nan |