Most Popular
1500 questions
7
votes
1 answer
How does the network know which objects to track in the paper "Label-Free Supervision of Neural Networks with Physics and Domain Knowledge"?
I was reading the paper Label-Free Supervision of Neural Networks with Physics and Domain Knowledge, published at AAAI 2017, which won the best paper award.
I understand the math and it makes sense. Consider the first application shown in the paper…
sanjeev mk
- 171
- 2
7
votes
1 answer
How do we determine whether a heuristic function is better than another?
I am trying to solve a maze puzzle using the A* algorithm. I am trying to analyze the algorithm based on different applicable heuristic functions.
Currently, I explored the Manhattan and Euclidean distances. Which other heuristic functions are…
m2rik
- 333
- 1
- 9
7
votes
2 answers
Why is the generation of deep style images so slow and resource-hungry?
Consider these neural style algorithms which produce some art work:
Neural Doodle
neural-style
Why is generating such images so slow and why does it take huge amounts of memory? Isn't there any method of optimizing the algorithm?
What is the…
kenorb
- 10,525
- 6
- 45
- 95
7
votes
5 answers
How can action recognition be achieved?
For example, I would like to train my neural network to recognize the type of actions (e.g. in commercial movies or some real-life videos), so I can "ask" my network in which video or movie (and at what frames) somebody was driving a car, kissing,…
kenorb
- 10,525
- 6
- 45
- 95
7
votes
2 answers
How would an AI learn idiomatic phrases in a natural language?
After an AI goes through the process described in How would an AI learn language?, an AI knows the grammar of a language through the process of grammar induction. They can speak the language, but they have learned formal grammar. But most…
Marvin
- 83
- 10
7
votes
2 answers
What is the current state-of-the-art in Reinforcement Learning regarding data efficiency?
In other words, which existing reinforcement method learns with fewest episodes? R-Max comes to mind, but it's very old and I'd like to know if there is something better now.
rcpinto
- 2,148
- 1
- 17
- 31
7
votes
4 answers
Are fully connected layers necessary in a CNN?
I have implemented a CNN for image classification. I have not used fully connected layers, but only a softmax. Still, I am getting results.
Must I use fully-connected layers in a CNN?
SARIKA
- 71
- 1
- 2
7
votes
1 answer
What is the difference between asymmetric and depthwise separable convolution?
I have recently discovered asymmetric convolution layers in deep learning architectures, a concept which seems very similar to depthwise separable convolutions.
Are they really the same concept with different names? If not, where is the difference?…
Pierre Gramme
- 183
- 5
7
votes
6 answers
Is randomness anti-logical?
I came across a comment recently "reads like sentences strung together with no logic." But is this even possible?
Sentences can be strung together randomly if the selection process is random. (Random sentences in a random sequence.) Stochasticity…
DukeZhou
- 6,209
- 5
- 27
- 54
7
votes
1 answer
What is the best measure for detecting overfitting?
I wanted to ask about the methodology of testing the ML models against overfitting. Please note that I don't mean any overfitting reducing methods like regularisation, just a measure to judge whether a model has overfitting problems.
I am currently…
GKozinski
- 1,290
- 11
- 22
7
votes
1 answer
How to avoid falling into the "local minima" trap?
How do I avoid my gradient descent algorithm into falling into the "local minima" trap while backpropogating on my neural network?
Are there any methods which help me avoid it?
Dawny33
- 1,381
- 13
- 29
7
votes
2 answers
Was the corruption of Microsoft's "Tay" chatbot an example of catastrophic forgetting?
Tay was a chatbot, who learned from Twitter users.
Microsoft's AI fam from the internet that's got zero chill. The more you talk the smarter Tay gets. — Twitter tagline.
Microsoft trained the AI to have a basic ability to communicate, and taught…
wizzwizz4
- 225
- 1
- 12
7
votes
2 answers
Can neuroevolution be combined with gradient descent?
Is there any precedent for using a neuroevolution algorithm, like NEAT, as a way of getting to an initialization of weights for a network that can then be fine-tuned with gradient descent and back-propagation?
I wonder if this may be a faster way…
benbyford
- 358
- 2
- 12
7
votes
1 answer
What are options in reinforcement learning?
According to a lecture (week 10) about Reinforcement Learning [1], the concept of an option allows searching the state space of an agent much faster. The lecture was hard to follow because many new terms were introduced in a short time. For me, the…
user11571
7
votes
1 answer
Why can a fully convolutional network accept images of any size?
On this article, it says that:
The UNET was developed by Olaf Ronneberger et al. for Bio Medical Image Segmentation. The architecture contains two paths. First path is the contraction path (also called as the encoder) which is used to capture the…
SDG
- 173
- 1
- 5