Most Popular
1500 questions
8
votes
4 answers
Should intelligent AI be granted the same rights as humans?
One of the most crucial questions we as a species and as intelligent beings will have to address lies with the rights we plan to grant to AI.
This question is intended to see if a compromise can be found between conservative anthropocentrism and…
GJZ
- 462
- 2
- 16
8
votes
2 answers
Why is the perceptron criterion function differentiable?
I'm reading chapter one of the book called Neural Networks and Deep Learning from Aggarwal.
In section 1.2.1.1 of the book, I'm learning about the perceptron. One thing that book says is, if we use the sign function for the following loss function:…
Flávio Mendes
- 83
- 4
8
votes
1 answer
Is there a connection between the bias term in a linear regression model and the bias that can lead to under-fitting?
Here is a linear regression model
$$y = mx + b,$$
where $b$ is known as $y$-intercept, but also known as the bias [1], $m$ is the slope, and $x$ is the feature vector.
As I understood, in machine learning, there is also the bias that can cause the…
Sivaram Rasathurai
- 316
- 2
- 10
8
votes
1 answer
Why is the learning rate generally beneath 1?
In all examples I've ever seen, the learning rate of an optimisation method is always less than $1$. However, I've never found an explanation as to why this is. In addition to that, there are some cases where having a learning rate bigger than 1 is…
Recessive
- 1,396
- 8
- 21
8
votes
1 answer
Which loss function should I use in REINFORCE, and what are the labels?
I understand that this is the update for the parameters of a policy in REINFORCE:
$$
\Delta \theta_{t}=\alpha \nabla_{\theta} \log \pi_{\theta}\left(a_{t} \mid s_{t}\right) v_{t},
$$
where $v_t$ is usually the discounted future reward and …
S2673
- 590
- 4
- 17
8
votes
2 answers
Are there transformer-based architectures that can produce fixed-length vector encodings given arbitrary-length text documents?
BERT encodes a piece of text such that each token (usually words) in the input text map to a vector in the encoding of the text. However, this makes the length of the encoding vary as a function of the input length of the text, which makes it more…
HelloGoodbye
- 313
- 1
- 11
8
votes
2 answers
What are some best practices when trying to design a reward function?
Generally speaking, is there a best-practice procedure to follow when trying to define a reward function for a reinforcement-learning agent? What common pitfalls are there when defining the reward function, and how should you avoid them? What…
12 rhombi in grid w no corners
- 195
- 1
- 8
8
votes
2 answers
How is the F1 score calculated in a question-answering system?
I have an NLP model for answer-extraction. So, basically, I have a paragraph and a question as input, and my model extracts the span of the paragraph that corresponds to the answer to the question.
I need to know how to compute the F1 score for such…
HLeb
- 579
- 5
- 10
8
votes
0 answers
Is the Bellman equation that uses sampling weighted by the Q values (instead of max) a contraction?
It is proved that the Bellman update is a contraction (1).
Here is the Bellman update that is used for Q-Learning:
$$Q_{t+1}(s, a) = Q_{t}(s, a) + \alpha*(r(s, a, s') + \gamma \max_{a^*} (Q_{t}(s',
a^*)) - Q_t(s,a)) \tag{1} \label{1}$$
The proof…
sirfroggy
- 81
- 3
8
votes
2 answers
What are the main algorithms used in computer vision?
Nowadays, CV has really achieved great performance in many different areas. However, it is not clear what a CV algorithm is.
What are some examples of CV algorithms that are commonly used nowadays and have achieved state-of-the-art performance?
Pluviophile
- 1,263
- 6
- 19
- 39
8
votes
3 answers
Is Artificial Intelligence restricted to electrical based technology?
According to Wikipedia:
AI is intelligence exhibited by machines.
I have been wondering if with the recent biological advancements, is there already a non-electrical-based "machine" that is programmed by humans in order to be able to behave like…
CPHPython
- 181
- 3
- 6
8
votes
2 answers
Why does the state-action value function, defined as an expected value of the reward and state value function, not need to follow a policy?
I often see that the state-action value function is expressed as:
$$q_{\pi}(s,a)=\color{red}{\mathbb{E}_{\pi}}[R_{t+1}+\gamma G_{t+1} | S_t=s, A_t = a] = \color{blue}{\mathbb{E}}[R_{t+1}+\gamma v_{\pi}(s') |S_t = s, A_t =a]$$
Why does expressing the…
Daniel Wiczew
- 343
- 2
- 11
8
votes
1 answer
Can deep learning be used to help mathematical research?
I am currently learning about deep learning and artificial intelligence and exploring his possibilities, and, as a mathematician at heart, I am inquisitive about how it can be used to solve problems in mathematics.
Seeing how well recurrent neural…
Antoine Labelle
- 141
- 6
8
votes
5 answers
Why are autonomous cars categorized as AI?
How are autonomous cars related to artificial intelligence? I would presume that artificial intelligence is when we are able to copy the human state of mind and perform tasks in the same way. But isn't an autonomous car just rule-based machines that…
Jamgreen
- 309
- 1
- 5
8
votes
4 answers
Why does this multiplication of $Q$ and $K$ have a variance of $d_k$, in scaled dot product attention?
In scaled dot product attention, we scale our outputs by dividing the dot product by the square root of the dimensionality of the matrix:
The reason why is stated that this constrains the distribution of the weights of the output to have a standard…
Jacob B
- 247
- 2
- 5