Most Popular

1500 questions
6
votes
3 answers

Why are traditional ML models still used over deep neural networks?

I'm still on my first steps in the Data Science field. I played with some DL frameworks, like TensorFlow (pure) and Keras (on top) before, and know a little bit of some "classic machine learning" algorithms like decision trees, k-nearest neighbors,…
Douglas Ferreira
  • 845
  • 1
  • 9
  • 13
6
votes
1 answer

What is the mathematical definition of an activation function?

What is the mathematical definition of an activation function to be used in a neural network? So far I did not find a precise one, summarizing which criterions (e.g. monotonicity, differentiability, etc.) are required. Any recommendations for…
6
votes
0 answers

Has anyone attempted to take a bunch of similar neural networks to extract general formulae about the focus area?

When a neural network learns something from a data set, we are left with a bunch of weights which represent some approximation of knowledge about the world. Although different data sets or even different runs of the same NN might yield completely…
Lawnmower Man
  • 300
  • 1
  • 7
6
votes
2 answers

How to understand the concept of self-supervised learning in AI?

I am new to self-supervised learning and it all seems a little magical at the moment. The only way I can get an intuitive understanding is to assume that, for real-world problems, features are still embedded at a per-object level. For example, to…
6
votes
1 answer

Interesting examples of discrete stochastic games

SGs are a generalization of MDPs to multiple agents. Like this previous question on MDPs, are there any interesting examples of zero-sum, discrete SGs—preferably with small state and action spaces? I'm hoping to use such examples as benchmarks, but…
6
votes
1 answer

Why was ELIZA able to induce "delusional thinking"?

From Eliza to A.L.I.C.E.: Weizenbaum tells us that he was shocked by the experience of releasing ELIZA (also known as "Doctor") to the nontechnical staff at the MIT AI Lab. Secretaries and nontechnical administrative staff thought the machine was a…
6
votes
2 answers

Why cannot an AI agent adjust the reward function directly?

In standard Reinforcement Learning the reward function is specified by an AI designer and is external to the AI agent. The agent attempts to find a behaviour that collects higher cumulative discounted reward. In Evolutionary Reinforcement Learning…
rodan
  • 61
  • 2
6
votes
2 answers

Does using the softmax function in Q learning not defeat the purpose of Q learning?

It is my understanding that, in Q-learning, you are trying to mimic the optimal $Q$ function $Q*$, where $Q*$ is a measure of the predicted reward received from taking action $a$ at state $s$ so that the reward is maximised. I understand for this to…
Recessive
  • 1,446
  • 10
  • 21
6
votes
1 answer

To deal with infinite loops, should I do a deeper search of the best moves with the same value, in alpha-beta pruning?

I have implemented minimax with alpha-beta pruning to play checkers. As my value heuristic, I am using only the summation of material value on the board regardless of the position. My main issue lays in actually finishing games. A search with depth…
6
votes
2 answers

Can CNNs be applied to non-image data, given that the convolution and pooling operations are mainly applied to imagery?

When using CNNs for non-image (times series) data prediction, what are some constraints or things to look out for as compared to image data? To be more precise, I notice there are different types of layers in a CNN model, as described below, which…
6
votes
1 answer

What is the relationship between robustness and adversarial machine learning?

I have been reading a lot of articles on adversarial machine learning and there are mentions of "best practices for robust machine learning". A specific example of this would be when there are references to "loss of efficient robust estimation in…
6
votes
0 answers

Are there any easy ways to create annotated training images for object detection?

For the purposes of object detection, are there any easy ways to create annotated training images? For example, if we have $10,000$ images and want to draw bounding boxes on 2 objects for each image, do we have to physically draw those boxes? Is…
6
votes
2 answers

How to deal with images of different sizes, which need to be passed to a model of fixed input size, without losing details and spatial information?

I have the following problem while using convolutional neural networks to detect forgeries: Resizing the image to fit the required input size may not be a good way because the forgery detection largely relies on the details of images, for example,…
6
votes
1 answer

How do artificial neural networks store data compared to biological neural networks?

Do scientists know by what mechanism biological brains/biological neural networks store data? I only have a vague notion that we store data in our brains by altering synapses. I also would love a decent description of how a vanilla artificial neural…
Conor Cosnett
  • 554
  • 5
  • 12
6
votes
3 answers

What is a "surrogate model"?

In the following paragraph from the book Automated Machine Learning: Methods, Systems, Challenges (by Frank Hutter et al.) In this section we first give a brief introduction to Bayesian optimization, present alternative surrogate models used in it,…