Most Popular
1500 questions
6
votes
2 answers
What is a good way to create an artificial self-recognition?
Self-Recognition seems to be an item that designers are trying to integrate into artificial intelligence. Is there a generally recognized method of doing this in a machine, and how would one test the capacity - as in a Turing-Test?
D. Wade
- 541
- 2
- 7
6
votes
5 answers
Emulating human brain - with analogous NN chips
Considering the answers of this question, emulating a human brain with the current computing capacity is currently impossible, but we aren't very far from it.
Note, 1 or 2 decades ago, similar calculations had similar results.
The clock frequency of…
peterh
- 203
- 4
- 16
6
votes
1 answer
How should I deal with variable-length inputs for neural networks?
I am a very beginner in the field of AI. I am basically a Pharma Professional without much coding experience. I use GUI-based tools for the neural network.
I am trying to develop an ANN that receives as input a protein sequence and produces as…
Swayamprakash Patel
- 91
- 4
6
votes
2 answers
Can neurons in MLP and filters in CNN be compared?
I know they are not the same in working, but an input layer sends the input to $n$ neurons with a set of weights, based on these weights and the activation layer, it produces an output that can be fed to the next layer.
Aren't the filters the same,…
Tibo Geysen
- 193
- 5
6
votes
1 answer
What are pros and cons of Bi-LSTM as compared to LSTM?
What are the pros and cons of LSTM vs Bi-LSTM in language modelling? What was the need to introduce Bi-LSTM?
DRV
- 1,673
- 3
- 13
- 19
6
votes
1 answer
If vanishing gradients are NOT the problem that ResNets solve, then what is the explanation behind ResNet success?
I often see blog posts or questions on here starting with the premise that ResNets solve the vanishing gradient problem.
The original 2015 paper contains the following passage in section 4.1:
We argue that this optimization difficulty is unlikely…
Alexander Soare
- 1,339
- 2
- 11
- 27
6
votes
0 answers
How to correctly implement self-play with DQN?
I have an environment where an agent faces an equal opponent, and while I've achieved OK performance implementing DQN and treating the opponent as a part of the environment, I think performance would improve if the agent trains against itself…
Pell000
- 61
- 1
6
votes
2 answers
How can the policy iteration algorithm be model-free if it uses the transition probabilities?
I'm actually trying to understand the policy iteration in the context of RL. I read an article presenting it and, at some point, a pseudo-code of the algorithm is given :
What I can't understand is this line :
From what I understand, policy…
Samuel Beaussant
- 193
- 3
6
votes
0 answers
How exactly does self-play work, and how does it relate to MCTS?
I am working towards using RL to create an AI for a two-player, hidden-information, a turn-based board game. I have just finished David Silver's RL course and Denny Britz's coding exercises, and so am relatively familiar with MC control, SARSA,…
Alienator
- 61
- 2
6
votes
2 answers
What are the state-of-the-art meta-reinforcement learning methods?
This question can seem a little bit too broad, but I am wondering what are the current state-of-the-art works on meta reinforcement learning. Can you provide me with the current state-of-the-art in this field?
Sara El
- 63
- 4
6
votes
1 answer
Why is the evidence equal to the KL divergence plus the loss?
Why is the equation $$\log p_{\theta}(x^1,...,x^N)=D_{KL}(q_{\theta}(z|x^i)||p_{\phi}(z|x^i))+\mathbb{L}(\phi,\theta;x^i)$$ true, where $x^i$ are data points and $z$ are latent variables?
I was reading the original variation autoencoder paper and I…
user8714896
- 797
- 1
- 6
- 24
6
votes
2 answers
In deep learning, is it possible to use discontinuous activation functions?
In deep learning, is it possible to use discontinuous activation functions (e.g. one with jump discontinuity)?
(My guess: for example, ReLU is non-differentiable at a single point, but it still has a well-defined derivative. If an activation…
Gyeonghoon Ko
- 61
- 2
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
- 8
- 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…
user32649
- 69
- 2
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