Artificial Intelligence Stack Exchange Community Digest

Top new questions this week:

Group image classification for whether containing unrelated images

I’m kind of new to computer vision, and wondering whether this is any existing researches / solutions to following scenarios. Suppose I have a dataset, each data point contains a few images (< 20 …

machine-learning deep-learning computer-vision attention

asked by misakayu Score of 1 answered by Dr. Snoopy Score of 1

Why MSE and MAE yield poor results when used with gradient-based optimization for classification?

Deep learning book chapter 6: In 6.2.1.2 last paragraph: Unfortunately, mean squared error and mean absolute error often lead to poor results when used with gradient-based optimization. Some output …

machine-learning deep-learning objective-functions deep-neural-networks

asked by VVY Score of 1 answered by Snehal Patel Score of 1

Why $V^{\pi^*}(s) = \max_{a \in A}Q^{\pi^*}(s,a),\forall s \in S$ in reinforcement learning?

When i read some notes about RL i encounterd following equation and try to prove it: $$ V^{\pi^*}(s) = \max_{a \in A}Q^{\pi^*}(s, a),\forall s \in S $$ Here is my attemption: Firstly, i only need to …

reinforcement-learning deep-rl

asked by vincen Score of 1

Are there free and open-source audio versions of Generative AI programs like Stable Diffusion?

Generative AI is being used to create amazing art; first through paid services like Midjourney and now also with free, open source alternatives like Stable Diffusion. Now you can even generate art in …

reference-request

asked by kanamekun Score of 1 answered by Edoardo Guerriero Score of 2

How can deep learning be used to improve our understanding of dark matter and dark energy?

Some possible ways deep learning could be used to improve our understanding of dark matter and dark energy are by using it to study the universe’s large-scale structure or to develop new methods for …

deep-learning convolutional-neural-networks agi

asked by Francis Score of 1

Greatest hits from previous weeks:

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 …

machine-learning recurrent-neural-networks prediction sequence-modeling

asked by ZenBerry Score of 6 answered by serali Score of 9

What is a Dynamic Computational Graph?

Frameworks like PyTorch and TensorFlow through TensorFlow Fold support Dynamic Computational Graphs and are receiving attention from data scientists. However, there seems to be a lack of resource to …

neural-networks

asked by Blaszard Score of 25 answered by Douglas Daseeco Score of 10

What are the advantages of ReLU vs Leaky ReLU and Parametric ReLU (if any)?

I think that the advantage of using Leaky ReLU instead of ReLU is that in this way we cannot have vanishing gradient. Parametric ReLU has the same advantage with the only difference that the slope of …

neural-networks activation-functions relu

asked by gvgramazio Score of 19 answered by Douglas Daseeco Score of 13

What is an objective function?

Local search algorithms are useful for solving pure optimization problems, in which the aim is to find the best state according to an objective function. My question is what is the objective function?

terminology objective-functions optimization local-search meta-heuristics

asked by Abbas Ali Score of 5 answered by nbro Score of 6

What is the purpose of an activation function in neural networks?

It is said that activation functions in neural networks help introduce non-linearity. What does this mean? What does non-linearity mean in this context? How does the introduction of this non-…

neural-networks deep-learning terminology activation-functions

asked by Mohsin Bukhari Score of 37 answered by Marcel_marcel1991 Score of 11

How is iterative deepening A* better than A*?

The iterative deepening A* search is an algorithm that can find the shortest path between a designated start node and any member of a set of goals. The A* algorithm evaluates nodes by combining the …

search comparison a-star ida-star

asked by Huma Qaseem Score of 6 answered by nbro Score of 11

What are bottleneck features?

In the blog post Building powerful image classification models using very little data, bottleneck features are mentioned. What are the bottleneck features? Do they change with the architecture that is …

machine-learning convolutional-neural-networks terminology definitions bottlenecks

asked by Abhishek Bhatia Score of 12 answered by FunkyKowal Score of 10