Most Popular
1500 questions
5
votes
1 answer
How could AI be used to augment human biological intelligence?
One of the most compelling applications for AI would be in augmenting human biological intelligence. What are some of the currently proposed methods for doing this aside from vague notions such as "nanobots swimming around our brains and bodies" or…
David Vogel
- 191
- 5
5
votes
1 answer
Does the input layer of a neural network have bias and are there bias neurons?
I have seen two different representations of neural networks when it comes to bias. Consider a "simple" neural network, with just an input layer, a hidden layer and an output layer. To compute the value of a neuron in the hidden layer, the weights…
Mark
- 153
- 1
- 4
5
votes
3 answers
Why would neural networks be a particularly good framework for "embodied AI"?
There is this claim around that the brain's cognitive capabilities are tightly linked to the way it processes sensorimotor information and that, in this or a similar sense, our intelligence is "embodied". Lets assume, for the sake of argument, that…
Paul
- 53
- 4
5
votes
3 answers
What is the purpose of hidden nodes in neural network?
If I have a set of sensory nodes taking in information and a set of "action nodes" which determine the behavior of my robot, why do I need hidden nodes between them when I can let all sensory nodes affect all action nodes?
(This is in the context of…
user289661
- 419
- 3
- 11
5
votes
2 answers
Do convolutional neural networks perform convolution or cross-correlation?
Typically, people say that convolutional neural networks (CNN) perform the convolution operation, hence their name. However, some people have also said that a CNN actually performs the cross-correlation operation rather than the convolution. How is…
nbro
- 40,454
- 12
- 105
- 192
5
votes
2 answers
Why isn't my decision tree classifier able to solve the XOR problem properly?
I was trying to solve an XOR problem, and the dataset seems like the one in the image.
I plotted the tree and got this result:
As I understand, the tree should have depth 2 and four leaves. The first comparison is annoying, because it is close to…
Pedro Paiva
- 53
- 4
5
votes
3 answers
What are the differences between a knowledge base and a knowledge graph?
During my readings, I have seen many authors using the two terms interchangeably, i.e. as if they refer to the same thing. However, we all know about Google's first quotation of "knowledge graph" to refer to their new way of making use of their…
Betty
- 151
- 2
- 7
5
votes
1 answer
Non-differentiable reward function to update a neural network
In Reinforcement Learning, when reward function is not differentiable, a policy gradient algorithm is used to update the weights of a network. In the paper Neural Architecture Search with Reinforcement Learning they use accuracy of one neural…
samsambakster
- 171
- 5
5
votes
1 answer
What are the differences between constraint satisfaction problems and linear programming?
I have taken an algorithms course where we talked about LP significantly, and also many reductions to LPs. As I recall, normal LP is not NP-Hard. Integer LP is NP-Hard. I am currently taking an introduction to AI course, and I was wondering if CSP…
Prabh Dhali
- 51
- 2
5
votes
1 answer
If the current state is $S_t$ and the actions are chosen according to $\pi$, what is the expectation of $R_{t+1}$ in terms of $\pi$ and $p$?
I'm trying to solve exercise 3.11 from the book Sutton and Barto's book (2nd edition)
Exercise 3.11 If the current state is $S_t$ , and actions are selected according to a stochastic policy $\pi$, then what is the expectation of $R_{t+1}$ in terms…
tmaric
- 382
- 2
- 9
5
votes
1 answer
How do I convert an MDP with the reward function in the form $R(s,a,s')$ to and an MDP with a reward function in the form $R(s,a)$?
The AIMA book has an exercise about showing that an MDP with rewards of the form $r(s, a, s')$ can be converted to an MDP with rewards $r(s, a)$, and to an MDP with rewards $r(s)$ with equivalent optimal policies.
In the case of converting to $r(s)$…
Asher
- 436
- 3
- 9
5
votes
2 answers
How can we compute the ratio between the distributions if we don't know one of the distributions?
Here is my understanding of importance sampling. If we have two distributions $p(x)$ and $q(x)$, where we have a way of sampling from $p(x)$ but not from $q(x)$, but we want to compute the expectation wrt $q(x)$, then we use importance sampling.…
pecey
- 333
- 2
- 10
5
votes
1 answer
How does being on-policy prevent us from using the replay buffer with the policy gradients?
One of the approaches to improving the stability of the Policy
Gradient family of methods is to use multiple environments in
parallel. The reason behind this is the fundamental problem we
discussed in Chapter 6, Deep Q-Network, when we talked about…
jgauth
- 261
- 1
- 12
5
votes
1 answer
What are the techniques for detecting and preventing overfitting?
I'm worrying that my neural network has become too complex. I don't want to end up with half of the neural network doing nothing but just take up space and resources.
So, what are the techniques for detecting and preventing overfitting, to avoid…
kenorb
- 10,483
- 3
- 44
- 94
5
votes
2 answers
What are the common pitfalls that we could face when training neural networks?
Apart from the vanishing or exploding gradient problems, what are other problems or pitfalls that we could face when training neural networks?
pjoter
- 51
- 1