Most Popular
1500 questions
9
votes
2 answers
What is an activity vector in capsule neural networks?
I was reading the paper Dynamic Routing Between Capsules and didn't understand the term "activity vector" in the abstract.
A capsule is a group of neurons whose activity vector represents the instantiation parameters of a specific type of entity…
tim_xyz
- 301
- 3
- 9
9
votes
2 answers
Can someone help me understand the intuition behind the query, key and value matrices in the transformer architecture?
I have been working mechanically with transformers, hoping that with time clarity about what the query, key, and value matrices represent will develop; but I am still lost. Would greatly benefit from a simplified explanation.
Chinmay
- 539
- 3
- 14
9
votes
4 answers
When to choose Stochastic Hill Climbing over Steepest Hill Climbing?
Stochastic Hill Climbing generally performs worse than Steepest Hill Climbing, but what are the cases in which the former performs better?
Rohan Sharma
- 91
- 1
- 4
9
votes
1 answer
How much of the ChatGPT output is copied from its training set (vs. being abstractively generated)?
One of the main concerns of using ChatGPT answers on Stack Exchange is that it may copy verbatim or almost verbatim some text from its training set, which may infringe the source text's license. This makes me wonder how much of the ChatGPT output is…
Franck Dernoncourt
- 3,473
- 2
- 21
- 39
9
votes
2 answers
What's the difference between Starcraft and Dota from an AI perspective?
So, Deepmind is pushing for a human level Starcraft bot and Open AI just created a human level 1vs1 Dota bot.
Unfortunately, I've no clue what that signifies because I've never played Starcraft nor Dota nor do I have more than a fleeting…
BlindKungFuMaster
- 4,265
- 13
- 23
9
votes
6 answers
If an event has a statistical probability of only 50%, is it possible to use a neural network to predict it with more than 50% accuracy?
For example using a neural network to predict a coin toss. Can a trained neural network to predict it with more than 50% accuracy?
huang
- 303
- 3
- 10
9
votes
1 answer
What are other ways of handling invalid actions in scenarios where all rewards are either 0 (best reward) or negative?
I created an OpenAI Gym environment, and I would like to check the performance of the agent from OpenAI Baselines DQN approach on it.
In my environment, the best possible outcome for the agent is 0 - the robot needs zero non-necessary resources to…
AlexGuevara
- 273
- 2
- 8
9
votes
3 answers
Can AI write good jokes yet?
Just watched a recent WIRED video on virtual assistants' performance on telling jokes. They're composed by humans, but I'd like to know if AI has gotten good enough to write some.
user7478
9
votes
4 answers
How can I predict the next number in a non-obvious sequence?
I've got an array of integers ranging from -3 to +3.
Example: [1, 3, -2, 0, 0, 1]
The array has no obvious pattern since it represents bipolar disorder mood swings.
What is the most suitable approach to predict the next number in the series? The…
ZenBerry
- 193
- 1
- 1
- 4
9
votes
1 answer
How powerful is the machine that beat the poker professional players recently?
How powerful is the machine that beat the poker professional players recently (DeepStack)?
user6411
- 99
- 1
9
votes
3 answers
What is the difference between the US and global edition of the AIMA book by Russell and Norvig?
The book Artificial Intelligence: A Modern Approach by Russell and Norvig has two editions: global and the US. It looks like these two are generally the same, but have some differences in the order of the chapters and in the context, is this…
Emad
- 237
- 2
- 7
9
votes
4 answers
Are AI winters inevitable?
According to Wikipedia (citations omitted):
In the history of artificial intelligence, an AI winter is a period of reduced funding and interest in artificial intelligence research. The term was coined by analogy to the idea of a nuclear winter. The…
Left SE On 10_6_19
- 1,670
- 10
- 23
9
votes
3 answers
What's the term for death by dissolving in AI?
What's the term (if such exists) for merging with AI (e.g. via neural lace) and becoming so diluted (e.g. 1:10000) that it effectively results in a death of the original self?
It's not quite "digital ascension", because that way it would still be…
ikaruss
- 201
- 1
- 4
9
votes
1 answer
How would one debug, understand or fix the outcome of a neural network?
It seems fairly uncontroversial to say that NN based approaches are becoming quite powerful tools in many AI areas - whether recognising and decomposing images (faces at a border, street scenes in automobiles, decision making in uncertain/complex…
Stilez
- 233
- 1
- 4
9
votes
1 answer
How much of a problem is white noise for the real-world usage of a DNN?
I read that deep neural networks can be relatively easily fooled (link) to give high confidence in recognition of synthetic/artificial images that are completely (or at least mostly) out of the confidence subject.
Personally, I don't really see a…
Kozuch
- 281
- 1
- 6