Most Popular
1500 questions
5
votes
3 answers
Is it possible to tell the Reinforcement Learning agent some rules directly without any constraints?
I try to apply RL for a control problem, and I intend to either use Deep Q-Learning or SARSA.
I have two heating storage systems with one heating device, and the RL agent is only allowed to heat up 1 for every time slot. How can I do that?
I have…
PeterBe
- 256
- 2
- 12
5
votes
1 answer
How to decide a train-test split?
In almost every ML model, a train-test (or train-test-val split) is critical to assess the model's performance. However, I have always wondered what the rationale is to decide a particular train-test split. I've seen that some people like an 80-20…
user48670
5
votes
1 answer
Why is the change in cost wrt bias in neural network equal to error in the neuron?
While reading the book on neural networks by Michael Nielson, I had a problem understanding equation (BP3), which is
$$
\frac{\partial C}{\partial b_{j}^{l}}=\delta_{j}^{l} \tag{BP3}\label{BP3},
$$
which can be translated to plain English as…
Madhusoodan P
- 151
- 1
- 4
5
votes
1 answer
Is there a widely accepted definition of the width of a neural network?
The depth of a neural network is equal to the total number of layers in the neural network (excluding the input layer by convention). A neural network with "many layers" is called a deep neural network.
On the other hand, the width is the name of a…
hanugm
- 3,820
- 3
- 24
- 56
5
votes
2 answers
Should I repeat lengthy deep learning experiments to average results ? How to decide how many times to repeat?
I am doing my MSc thesis on deep learning. My model takes many hours to train. Part of what I do is trying different parameters and settings hoping that they will achieve different results. But I often notice that the result differences are too…
Manveru
- 221
- 1
- 3
5
votes
2 answers
What is the difference between edge computing and federated learning?
I recently read about federated learning introduced by Google, but it seems to be like edge computing.
What is the difference between edge computing and federated learning?
Karan Nadagoudar
- 285
- 1
- 5
5
votes
3 answers
Can I always use "encoding" and "embedding" interchangeably?
This question is restricted to the text domain only.
The meaning of the word "encode" is Convert (information or instruction) into a particular form. One which performs encoding is called an encoder.
In deep learning, an encoder can also be the…
hanugm
- 3,820
- 3
- 24
- 56
5
votes
2 answers
Can an AGI convince another AGI to modify its code?
Let's suppose there are two AGIs, $A$ and $B$. Assume that $B$ has the ability to modify $A$, but this action of modifying is considered bad by $B$. Can $A$ ever convince $B$ to modify $A$?
Logan Young
- 61
- 4
5
votes
1 answer
What is expectation-maximization in machine learning?
While studying machine learning algorithms, I often see the term "expectation-maximisation" (or EM), and how it is used to estimate parameters, where the model depends on unobserved latent variables.
The way I see it, it is like a…
Guest2000
- 305
- 1
- 4
5
votes
1 answer
How do recommendation systems work?
How do recommendation systems (e.g. on Youtube) work? Apparently, every user gets different recommendations depending on his location, his past liked videos, etc. So it would seem like a training model is applied to every single user, but that can't…
Guest2000
- 305
- 1
- 4
5
votes
1 answer
When would you use Evolutionary Strategies over Step-Based Reinforcement Learning
In Salimans et al, 2016, the authors argue that ES should be considered a competitive alternative to MDP-based RL algorithms like Q-Learning, TRPO.
However, in practice, I notice that more often than not ES takes far more episodes to converge than…
ganto
- 151
- 1
5
votes
1 answer
What's the difference between a "perceptron" and a GLM?
In a comment to this question user nbro comments:
As a side note, "perceptrons" and "neural networks" may not be the same thing. People usually use the term perceptron to refer to a very simple neural network that has no hidden layer. Maybe you…
R.M.
- 308
- 1
- 6
5
votes
2 answers
Are calculus and differential geometry required for building neural networks?
I've been studying geometry and linear algebra for months with the goal to build neural networks. But now I'm reading that perceptrons require fitting curves, and curves are not expressed as linear functions. So, I might need to study differential…
user456280
- 171
- 5
5
votes
2 answers
How to check whether my loss function is convex or not?
Loss functions are useful in calculating loss and then we can update the weights of a neural network. The loss function is thus useful in training neural networks.
Consider the following excerpt from this answer
In principle, differentiability is…
hanugm
- 3,820
- 3
- 24
- 56
5
votes
3 answers
What is Lipschitz constraint and why it is enforced on discriminator?
The following is the abstract for the research paper titled Improved Training of Wasserstein GANs
Generative Adversarial Networks (GANs) are powerful generative models,
but suffer from training instability. The recently proposed
Wasserstein GAN…
hanugm
- 3,820
- 3
- 24
- 56