Community Digest

Top new questions this week:

How does the generator in GAN's work?

After reading a lot of articles (for instance, this one -, I've been wondering: how does the generator in GAN's work? What is the input ...

deep-learning generative-adversarial-networks  
asked by Shir K 6 votes
answered by Djib2011 1 vote

What is the formula for the momentum and Adam optimisers?

In the gradient descent algorithm, the formula to update the weight $w$, which has $g$ as the partial gradient of the loss function with respect to it, is: $$w\ -= r \times g$$ where $r$ is the ...

machine-learning gradient-descent momentum adam optimizers  
asked by datdinhquoc 6 votes
answered by Neil Slater 7 votes

Why Monte Carlo epsilon-soft approach cannot compute $\max Q(s,a)$?

I am new to Reinforcement learning and am currently reading up on the estimation of Q $\pi(s, a)$ values using MC epsilon-soft approach and chanced upon this algorithm. The link to the algorithm is ...

reinforcement-learning q-learning monte-carlo  
asked by calveeen 3 votes
answered by Neil Slater 2 votes

Can we get the inverse of the function that a neural network represents?

I was wondering if it's possible to get the inverse of a neural network. If we view a NN as a function, can we obtain its inverse? I tried to build a simple MNIST architecture, with the input of ...

neural-networks deep-learning python math  
asked by David Refaeli 3 votes
answered by respectful 1 vote

RNN models displays upper limit on predictions

I have trained a RNN, GRU, and LSTM on the same dataset, and looking at their respective predictions I have observed, that they all display an upper limit on the value they can predict. I have ...

recurrent-neural-networks long-short-term-memory prediction gated-recurrent-unit  
asked by Kornephoros 3 votes

How can a DQN backpropagate its loss?

I'm currently trying to take the next step in deep learning. I managed so far to write my own basic feed-forward network in python without any frameworks (just numpy and pandas), so I think I ...

deep-learning reinforcement-learning q-learning backpropagation dqn  
asked by OleVoß 3 votes
answered by Neil Slater 0 votes

What's the function that SGD takes to calculate the gradient?

I'm struggling to fully understand the stochastic gradient descent algorithm. I know that gradient descent allows you to find the local minimum of a function. What I don't know is what exactly that ...

neural-networks deep-learning backpropagation loss-functions gradient-descent  
asked by Dennis Orlando 3 votes
answered by Recessive 3 votes

Greatest hits from previous weeks:

What are some examples of intelligent agents for each intelligent agent class?

There are several classes of intelligent agents, such as: simple reflex agents model-based reflex agents goal-based agents utility-based agents learning agents Each of these agents behaves ...

definitions intelligent-agent multi-agent-systems  
asked by practronix512 6 votes
answered by amjad khatabi 6 votes

What is non-Euclidean data?

What is non-Euclidean data? Where does this type of data arises? Apparently, graphs and manifolds are non-Euclidean data. Why exactly is that the case? What is the difference between non-Euclidean and ...

machine-learning deep-learning datasets graphs geometric-deep-learning  
asked by nbro 2 votes
answered by Jaden Travnik 6 votes

What is the time complexity for training a neural network using back-propagation?

Suppose that a NN contains $n$ hidden layers, $m$ training examples, $x$ features, and $n_i$ nodes in each layer. What is the time complexity to train this NN using back-propagation? I have a basic ...

neural-networks machine-learning backpropagation time-complexity  
asked by DuttaA 16 votes
answered by M.kazem Akhgary 9 votes

How to train a neural network for a round based board game?

I'm wondering how to train a neural network for a round based board game like, tic-tac-toe, chess, risk or any other round based game. Getting the next move by inference seems to be pretty straight ...

training tensorflow game-ai  
asked by soriak 11 votes
answered by DukeZhou 10 votes

What is the difference between an agent function and an agent program?

What is the difference between an agent function and an agent program (with respect to the percept sequence)? In the book "Artificial Intelligence: A modern approach", The agent function, ...

terminology comparison ai-a-modern-approach  
asked by Abhishek Bhatia 4 votes
answered by NietzscheanAI 6 votes

What is a Dynamic Computational Graph?

Frameworks like PyTorch and TensorFlow through TensorFlow Fold support Dynamic Computational Graphs and are receiving attention from data scientists. However, there seems to be a lack of resource to ...

asked by Blaszard 19 votes
answered by Douglas Daseeco 8 votes

Permutation invariant neural networks

Given a neural network $f$ that takes as input $n$ data points: $x_1, \dots, x_n$. We say $f$ is permutation invariant if $$f(x_1 ... x_n) = f(pi(x_1 ... x_n))$$ for any permutation $pi$. ...

neural-networks machine-learning reference-request  
asked by Josef Ondrej 14 votes
answered by BlueMoon93 2 votes

Can you answer these questions?

NoisyNet DQN with default parameters not exploring

I implemented a DQN algorithm that plays OpenAIs Cartpole environment. The NN architecture consists of 3 normal linear layers that encode the state, and one noisy linear layer, that predicts the Q ...

reinforcement-learning dqn  
asked by Luca Thiede 1 vote
answered by Diego Gomez 0 votes

Training dataset for convolutional neural network classification - will images captured on the ground be useful for training aerial imagery?

I am an agronomy graduate student looking to classify crops from weeds using convolutional neural networks (CNNs). The basic idea that I am wanting to get into involves separating crops from weeds ...

machine-learning deep-learning convolutional-neural-networks image-recognition training  
asked by ihb 1 vote

Reinforcement learning CNN input weakness

I'm trying to train a network to navigate a 48x48 2D grid, and switch pixels from on to off or off to on. The agent receives a small reward if correct, and small punishment if incorrect pixel plotted. ...

reinforcement-learning convolutional-neural-networks  
asked by SumakuTension 1 vote
You're receiving this message because you subscribed to the Artificial Intelligence community digest.
Unsubscribe from this community digest       Edit email settings       Leave feedback       Privacy
Stack Overflow

Stack Overflow, 110 William Street, 28th floor, New York, NY 10038