Most Popular
1500 questions
12
votes
8 answers
What are the advantages of having self-driving cars?
What are the advantages of having self-driving cars?
We will be able to have more cars in the traffic at the same time, but won't it also make more people choose to use the cars, so both the traffic and the public health will actually become…
Jamgreen
- 309
- 1
- 5
12
votes
2 answers
What exactly is averaged when doing batch gradient descent?
I have a question about how the averaging works when doing mini-batch gradient descent.
I think I now understood the general gradient descent algorithm, but only for online learning. When doing mini-batch gradient descent, do I have to:
forward…
Ben
- 455
- 3
- 11
12
votes
8 answers
Why is search important in AI?
Why is search important in AI? What kinds of search algorithms are used in AI? How do they improve the result of an AI?
Zoltán Schmidt
- 643
- 7
- 14
12
votes
2 answers
Is anybody still using Conceptual Dependency Theory?
Roger Schank did some interesting work on language processing with Conceptual Dependency (CD) in the 1970s. He then moved somewhat out of the field, being in Education these days. There were some useful applications in natural language generation…
Oliver Mason
- 5,477
- 14
- 32
12
votes
3 answers
Are there any rules of thumb for having some idea of what capacity a neural network needs to have for a given problem?
To give an example. Let's just consider the MNIST dataset of handwritten digits. Here are some things which might have an impact on the optimum model capacity:
There are 10 output classes
The inputs are 28x28 grayscale pixels (I think this…
Alexander Soare
- 1,379
- 3
- 12
- 28
12
votes
1 answer
What are hyper-heuristics, and how are they different from meta-heuristics?
I wanted to know what the differences between hyper-heuristics and meta-heuristics are, and what their main applications are. Which problems are suited to be solved by hyper-heuristics?
bmwalide
- 399
- 2
- 6
12
votes
2 answers
Is there any existing attempt to create a deep learning model which extracts vector paths from bitmaps?
I need an algorithm to trace simple bitmaps, which only contain paths with a given stroke width.
Is there any existing attempt to create a deep learning model which extracts vector paths from bitmaps?
It is obviously very easy to generate bitmaps…
arthur.sw
- 171
- 1
- 8
12
votes
4 answers
Counterexamples to the reward hypothesis
On Sutton and Barto's RL book, the reward hypothesis is stated as
that all of what we mean by goals and purposes can be well thought of as the maximization of the expected value of the cumulative sum of a received scalar signal (called…
Bananin
- 221
- 1
- 5
12
votes
1 answer
Are humans superior to machines in chess?
A friend of mine, who is an International Master at chess, told me that humans were superior to machines provided you didn't impose the time constraints that exist in competitive chess (40 moves in 2 hours) since very often games were lost, to…
grandtout
- 221
- 2
- 5
12
votes
1 answer
What are all the different kinds of neural networks used for?
I found the following neural network cheat sheet (Cheat Sheets for AI, Neural Networks, Machine Learning, Deep Learning & Big Data).
What are all these different kinds of neural networks used for? For example, which neural networks can be used for…
Dan D
- 1,318
- 1
- 14
- 39
12
votes
0 answers
Extending FaceNet’s triplet loss to object recognition
FaceNet uses a novel loss metric (triplet loss) to train a model to output embeddings (128-D from the paper), such that any two faces of the same identity will have a small Euclidean distance, and such that any two faces of different identities will…
rossignol
- 121
- 4
12
votes
5 answers
Why do we need common sense in AI?
Let's consider this example:
It's John's birthday, let's buy him a kite.
We humans most likely would say the kite is a birthday gift, if asked why it's being bought; and we refer to this reasoning as common sense.
Why do we need this in…
Titan
- 133
- 1
- 7
12
votes
1 answer
What are the advantages of complex-valued neural networks?
During my research, I've stumbled upon "complex-valued neural networks", which are neural networks that work with complex-valued inputs (probably weights too). What are the advantages (or simply the applications) of this kind of neural network over…
rcpinto
- 2,148
- 1
- 17
- 31
12
votes
2 answers
How much of Deep Mind's work is actually reproducible?
DeepMind has published a lot of works on deep learning in the last years, most of them are state-of-the-art on their respective tasks. But how much of this work has actually been reproduced by the AI community? For instance, the Neural Turing…
rcpinto
- 2,148
- 1
- 17
- 31
12
votes
2 answers
Why don't people use nonlinear activation functions after projecting the query key value in attention?
Why don't people use nonlinear activation functions after projecting the query key value in attention?
It seems like doing this would lead to much-needed nonlinearity, otherwise, we're just doing linear transformations.
This observation applies to…
user3180
- 648
- 5
- 15