Most Popular
1500 questions
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
- 599
- 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
- 1,293
- 7
- 20
- 40
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
- 7
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
- 279
- 2
- 7
8
votes
2 answers
What is the difference between the prediction and control problems in the context of Reinforcement Learning?
What is the difference between the prediction (value estimation) and control problems in reinforcement learning?
Are there scenarios in RL where the problem cannot be distinctly categorised into the aforementioned problems and is a mixture of the…
user9947
8
votes
2 answers
What is the point of using 1D and 2D convolutions with a kernel size of 1 and 1x1 respectively?
I understand the gist of what convolutional neural networks do and what they are used for, but I still wrestle a bit with how they function on a conceptual level. For example, I get that filters with kernel size greater than 1 are used as feature…
Arcturai
- 81
- 1
8
votes
1 answer
Is the AI Effect caused by bad tests of intelligence?
According to Wikipedia...
The AI effect occurs when onlookers discount the behavior of an artificial intelligence program by arguing that it is not real intelligence.
Pamela McCorduck writes: "It's part of the history of the field of artificial…
Left SE On 10_6_19
- 1,670
- 10
- 23
8
votes
1 answer
Why do we update all layers simultaneously while training a neural network?
Very deep models involve the composition of several functions or layers. The gradient tells how to update each parameter, under the assumption that the other layers do not change. In practice, we update all of the layers simultaneously.
The above…
stoic-santiago
- 1,201
- 9
- 22
8
votes
2 answers
How can I handle overfitting in reinforcement learning problems?
So this is my current result (loss and score per episode) of my RL model in a simple two players game:
I use DQN with CNN as a policy and target networks. I train my model using Adam optimizer and calculate the loss using Smooth L1 Loss.
In a…
malioboro
- 2,859
- 3
- 23
- 47
8
votes
2 answers
Is anybody still researching GOFAI?
A lot of textbooks and introductory lectures typically split AI into connectionism and GOFAI (Good Old Fashioned AI). From a purely technical perspective, it seems that connectionism has grown into machine learning and data science, while nobody…
Alex S King
- 251
- 1
- 6
8
votes
2 answers
What are some online courses for deep reinforcement learning?
What are some (good) online courses for deep reinforcement learning?
I would like the course to be both programming and theoretical. I really liked David Silver's course, but the course dates from 2015. It doesn't really teach deep Q-learning at…
J.Doe
- 91
- 3