All Questions

Filter by
Sorted by
Tagged with
0
votes
1answer
17 views

Why aren’t heuristics for Connect Four Monte Carlo tree search improving the agent?

I’ve created an agent using MCTS to play Connect Four. It wins against humans pretty well, but I’d like to improve upon it. I decided to add domain knowledge to the MCTS rollout stage. My evaluation ...
0
votes
0answers
16 views

DQN not showing the agent is learning in a snake grid environment game

I've been trying to train a snake for the snake game in DQN. Which the snake can essentially just move up, down, left and right. I'm having a hard time getting the snake to stay alive longer. So my ...
2
votes
1answer
193 views

Why isn't my implementation of A2C for the the atari pong game converging?

I have two different implementations with PyTorch of the Atari Pong game using A2C algorithm. Both implementations are similar, but some portion are different. https://colab.research.google.com/drive/...
0
votes
0answers
6 views

running model.evaluate many times results different accuracy and loss value tensorflow 2 [migrated]

I have trained a CNN network using dataset = tf.data.Dataset.from_tensor_slices((data, label)) to create the dataset. training went well but evaluating the model on ...
2
votes
1answer
43 views

How to evaluate a Deep Q-Network

Good day, it's a pleasure having joined this Stack. In my master thesis I have to expand a Deep Reinforcement Learning Network, to be precise a Deep Q-Network, which is used to control machines in an ...
3
votes
0answers
16 views

Conversion of strided filter gradient to convolutional form

I'm implementing strided 2D convolution. My formula looks like this: $$y_{i, j} = \sum_{m=0}^{F_h - 1}\sum_{n=0}^{F_w - 1} x_{s\cdot i + m, s\cdot j + n}\,f_{m, n}, \tag{1}$$ where $s$ is the stride (...
4
votes
1answer
30 views

How can I make ELIZA more realistic?

I’ve coded a simple ELIZA chatbot for a high school coding competition. The chatbot is part of an app that’s designed to help its user cope with depression, anxiety, and similar mental health ...
0
votes
1answer
72 views

Is my understanding of how AI works correct?

In my discussion over my question on Math SE, I explained to a user, how I think AI works, I wrote that with the sigmoid(logistic) function, features of a data set are identified, many such iterations ...
0
votes
0answers
7 views

How many spectrogram frames per input character does text-to-speech (TTS) system Tacotron-2 generate?

I've been reading on Tacotron-2, a text-to-speech system, that generates speech just-like humans (indistinguishable from humans) using the GitHub https://github.com/Rayhane-mamah/Tacotron-2. I'm very ...
2
votes
2answers
134 views

Advantage computed the wrong way?

Here is the code written by Maxim Lapan. I am reading his book (Deep Reinforcement Learning Hands-on). I have seen a line in his code which is really weird. In the accumulation of the policy gradient $...
3
votes
1answer
83 views

How to fill missing values in a dataset where some properties can be inputs and outputs?

I have a dataset with missing values, I would like to use machine learning methods to fill. In more detail, there are $n$ individuals, for which up to 10 properties are provided, all numerical. The ...
2
votes
1answer
50 views

In what RL algorithm category is MiniMax?

Q-learning is a temporal-difference method and Monte Carlo tree search is a Monte Carlo method. In what category is MiniMax?
0
votes
0answers
11 views

Fitting models to 2d data [migrated]

I am reading the documentation on tf.lattice (https://www.tensorflow.org/lattice/overview) I am wondering how the training data was created/trained. Is it represented by (x,y) intpositions and some ...
0
votes
0answers
5 views

Super-Resolution with Convolutional Neuronal Networks, why interpolation at the beginning?

I have read several papers about super-resolution with CNNs, where a low-resolution image is reconstructed to a high-resolution image. What I don't understand is, why it is necessary to interpolate ...
6
votes
2answers
58 views

Where to publish replications of machine learning papers?

If I replicated the results of a machine learning paper, is there a website that I can publish my code to that collects informal replication attempts? https://paperswithcode.com/ allows anyone to ...
1
vote
0answers
9 views

Solution for 'mixing' images

I want to feed the Neural Net with examples of three images: 2 input and one output-result. Net shold learn by those examples and then generate the appropriate "mixes" for new pairs of pics. Is there ...
16
votes
3answers
4k views

Why do most deep learning papers not include an implementation?

I'm a novice researcher, and as I started to read papers in the area of deep learning I noticed that the implementation is normally not added and is needed to be searched elsewhere, and my question is ...
4
votes
2answers
156 views

What is the difference between 'prediction' and 'control' problem in the context of Reinforcement Learning?

What is the difference between the term 'prediction'/value estimation in RL as compared to the 'control' problem? Are there scenarios in RL where the problem cannot be distinctly categorised into ...
2
votes
0answers
20 views

Is there an online RL algorithm that receives as input a camera frame and produces an action as output?

I want to build a reinforcement learning model, which takes a camera picture as input, that learns online (in terms of machine learning). Based on the position of an object on the camera, I want the ...
2
votes
0answers
9 views

Why is ANFIS important in general?

I am actually working with the iris dataset from sklearn and try to understand the ANFIS-Package for python. But that does not really matter! I have a more general question. During thinking about ...
3
votes
1answer
27 views

Effect of the order of the reward function

I have implemented a simple Q-learning algorithm to minimize a cost function by setting the reward to the inverse of the cost of the action taken by the agent. The algorithm converges nicely but there ...
2
votes
0answers
9 views

What is the difference between fuzzy neural networks and adaptive neuro fuzzy inference systems?

I have, like you see, just a general question about the combination of fuzziness and neural networks. I understood it as follows Fuzzy neural networks as a hybrid system: the neural network helps me ...
1
vote
0answers
17 views

Benchmarking SAC on Pybullet

So far I have seen TD3 and DDPG benchmarks on Pybullet environments, but I am looking for SAC benchmarks on Pybullet too, anyone can help?
1
vote
1answer
32 views

Are my steps correct for a proper classification of a sick brain?

I have a dataset with MRI of patients with a specific disease that affects the brain and another dataset with MRI of healthy patients. I want to create a classifier (using neural networks) to ...
3
votes
2answers
41 views

What is the difference between artificial intelligence and swarm intelligence?

Artificial intelligence (AI) refers to the simulation of human intelligence in machines that are programmed to think like humans and mimic their actions. The term may also be applied to any machine ...
0
votes
0answers
11 views

What are swarm optimization techniques used for: training the ANN by weight optimization or for feature selection?

Swarm intelligence (SI) is the collective behavior of decentralized, self-organized systems, natural or artificial. The concept is employed in work on artificial intelligence. SI-based algorithms, ...
1
vote
1answer
29 views

Is it possible to prove that the target policy is better than the behavioural policy based on learned Q values?

I have retrospective data for a sort of "behaviour policy" which I will use to train a deep q network to learn a target greedy policy. After learning the Q values for this target policy, can we make ...
2
votes
0answers
22 views

Does L1/L2 Regularization help reach an optimum result faster?

So I understand that L1 and L2 regularization helps to prevent overfitting. My question is then, does that mean they also help a neural network learn faster as a result? The way I'm thinking is that ...
0
votes
0answers
10 views

Run two jobs in parallel in one GPU [migrated]

Running on tensorflow, the moment that I try and run two jobs in parallel with any gpu related jobs, it flags and gives me an error regarding cuDNN module being not available. Is there any method ...
2
votes
0answers
21 views

Why do we use a weighted average of child entropies when we calculate information gain?

In the decision tree algorithm, why do we use a weighted average of child entropies when we calculate information gain? What is wrong about using the arithmetic mean of entropies?
2
votes
0answers
10 views

Why do hypercube latent spaces perform poorer than Gaussian latent spaces in generative neural networks?

I have a quick question regarding the use of different latent spaces to represent a distribution. Why is it that a Gaussian is usually used to represent the latent space of the generative model ...
3
votes
1answer
40 views

Would you categorize policy iteration as an actor-critic reinforcement learning approach?

One way of understanding the difference between value function approaches, policy approaches and actor-critic approaches in reinforcement learning is the following: A critic explicitly models a value ...
2
votes
1answer
30 views

Is the test time the phase when the model's accuracy is calculated with test data set?

When papers talk about the "test time", does this mean the phase when the model is passed with new data instances to derive the accuracy of the test data set? Or is "test time" the phase when the ...
3
votes
1answer
23 views

What should the dimension of the input be for text summarization?

I am trying to build a model for extractive text summarization using keras sequential layers. I am having a hard time trying to understand how to input my x data. Should it be an array of documents ...
2
votes
0answers
36 views

Does Gödel's second incompleteness theorem put a limitation on artificial intelligence systems?

According to Brian Cantwell Smith no calculation without representation Therefore, computers depend on models. So, we can say that AI is limited internally by the model and external by the ...
4
votes
1answer
52 views

How is the Jacobian a generalisation of the gradient?

I came across these slides Natural Language Processing with Deep Learning CS224N/Ling284, in the context of natural language processing, which talk about the Jacobian as a generalization of the ...
2
votes
0answers
34 views

How to calculate the data noise variance for a prediction interval?

I have a neural network that connects $N$ input variables to $M$ output variables (qoi). By default, neural networks just give out point estimations. Now, I want to plot some of the quantity of ...
3
votes
2answers
33 views

Calculating accuracy for cross validation

I'm struggling with calculating accuracy when I do cross-validation for a deep learning model. I have two candidates for doing this. 1. Train a model with 10 different folds and get the best accuracy ...
2
votes
1answer
66 views

On-policy preventing us from using the replay buffer with the PG?

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 ...
1
vote
0answers
13 views

Importance sampling eq. 5 in paper “Residual Energy-based Models for Text Generation”

In the paper "Residual Energy-Based Models for Text Generation" (arXiv), on page 5, they write that equation 5 is an instance of importance sampling. Equation 5 is: $$ P(x_t \mid x_{<t}) = P_{LM}(...
1
vote
1answer
27 views

Why a single trajectory can be used to update the policy network $\theta$ in A3C?

The Deep RL bootcamp on policy gradient techniques gives the update equation for the policy network in A3C as $\theta_{i+1} = \theta_i + \alpha \times 1/m \sum_{k=1}^m\sum_{t=0}^{H-1}\nabla_{\theta}...
3
votes
0answers
18 views

How do reinforcement learning and collaborative learning overlap?

How do reinforcement learning and collaborative learning overlap? What are the differences and similarities between these fields? I feel like the results I get via google do not make the distinction ...
1
vote
0answers
20 views

What pre-processing of the image is needed before feeding it into the convolutional neural network?

I can't figure out what preprocessing of the image is needed before feeding it into the convolutional neural network. For example, I want to recognize circles on a 1000 by 1000 px photo. The learning ...
1
vote
2answers
58 views

How does the gradient increase the probabilities of the path with a positive reward in policy gradient?

Pieter Abbeel in his deep rl bootcamp policy gradient lecture derived the gradient of the utility function with respect to $\theta$ as $\nabla U(\theta) \approx \hat{g} = 1/m\sum_{i=1}^m \nabla_\...
1
vote
0answers
9 views

Sentence Segmentation for “Bullets & Numbering”

I am trying to input text into my word processor to be split into sentences first and then into words. An example paragraph: ...
0
votes
0answers
18 views

Do we scale our target feature in regression problems?

I know this is a basic problem, but still could not find answer, I feel like most books/tutorials avoid talking about scaling the output feature instead they just mention scaling input features. So ...
0
votes
1answer
13 views

What are non-held-out data or non-held-out classes?

I'm Spanish and I don't understand the meaning of "non-held-out". I have tried Google Translator and online dictionaries like Longman but I can't find a suitable translation for this term. You can ...
0
votes
0answers
12 views

How's the action represented in MuZero for Atari?

MuZero seems to use two different methods to encode actions into planes for Atari games: For the input action to the representation function, MuZero encodes historical actions as simple bias planes, ...
2
votes
0answers
50 views

Can we use a Gaussian process to approximate the belief distribution at every instant in a POMDP?

Suppose $x_{t+1} \sim \mathbb{P}(\cdot | x_t, a_t)$ denotes the state transition dynamics in a reinforcement learning (RL) problem. Let $y_{t+1} = \mathbb{P}(\cdot | x_{t+1})$ denote the noisy ...
0
votes
0answers
10 views

what will be the best loss function for unet to predict the each pixel values?

I'm predicting the used 9 pictures to predict the last picture so (40,40,9) -> unet -> (40,40,1) but as you see the predict picture It's not just a mask(0or 1) its float so which loss function ...

15 30 50 per page