All Questions

Filter by
Sorted by
Tagged with
2
votes
0answers
30 views

How to control the switches of a railway track with Artificial Intelligence?

Usually, it's very complicated to program a real time strategy game from scratch. Notable examples like Lemmings or Starcraft are software projects with a large amount of codelines. A much easier ...
1
vote
0answers
14 views

Intelligent reflecting surface

I wanted to know about Intelligent reflecting surface (IRS) technology. what is the application of IRS in wireless communication? what are the competitive advantages over existing technologies?
3
votes
1answer
29 views

Why does having a fixed policy change a Markov Decision Process (MDP) to a Markov Reward Process (MRP)?

If a policy is fixed, it is said that an MDP becomes an MRP. Why is this so? Aren't the transitions and rewards still parameterized by the action and current state? In other words, aren't the ...
4
votes
2answers
55 views

Why is having low variance important in offline policy evaluation of reinforcement learning?

Intuitively, I understand that having an unbiased estimate of a policy is important because being biased just means that our estimate is distant from the truth value. However, I don't understand ...
5
votes
1answer
37 views

Why do very deep non resnet architectures perform worse compared to shallower ones for the same iteration? Shouldn't they just train slower?

My understanding of the vanishing gradient problem in deep networks is that as backprop progresses through the layers the gradients become small, and thus training progresses slower. I'm having a hard ...
8
votes
1answer
147 views

What are the implications of the “No Free Lunch” theorem for machine learning?

The No Free Lunch (NFL) theorem states (see the paper Coevolutionary Free Lunches by David H. Wolpert and William G. Macready) any two algorithms are equivalent when their performance is averaged ...
5
votes
0answers
32 views

Question about minimizing sum of remainders

I have a set of integers [$c_1$, $c_2$, $c_3$, ... , $c_N$]. A non-negative integer D, greater than a certain threshold, divides each 𝑐𝑖 and leaves remainder 𝑟𝑖,i.e., $r_i$ can be written as $r_i=...
3
votes
1answer
30 views

CNN how can i reduce gpu memory usage with large image sizes?

I am trying to train a cnn-lstm model, my sample image sizes are 640x640. I have a GTX 1080 ti 11GB. I am using Keras with tensorflow backend. Here is the model. ...
0
votes
0answers
12 views

Mapping model types to GPU Requirements

GPU are available in 6,8,&11 Gigabyte increments. I would like to understand the thought process and questions should be asked when deciding which of the 3 memory sizes is to be chosen. The ...
2
votes
0answers
37 views

CNN clasification model loss stuck at same value

I have CNN model to classify 2 classes. (Yes or No) I use categorical_crossentropy loss and softmax activation at the end. For input I use image with all 3 channels, for output I use One hot encoded ...
3
votes
1answer
49 views

What is the best variant of darknet to use?

pjreddie's official darknet version (link from official website here) has been forked several times. In particular I've come accross AlexeyAB's fork through this tutorial. I assume the tutorial's ...
3
votes
1answer
32 views

Why is batch gradient descent performing worse than stochastic and minibatch gradient descent?

I have implemented a neural network from scratch (only using numpy) and I am having problems understanding why the results are so different between stochastic/minibatch gradient descent and batch ...
2
votes
0answers
25 views

how to use Softmax action selection algorithm in atari-like game

I'm currently writing a program using keras (python 3) to play a game similar to Atari games, only in this one there are objects moving in the screen in different angles and directions (in most of ...
3
votes
0answers
41 views

What Is The Predicted Timeline for Driver-less Metros in Worldwide?

The technical challenge of introducing rail-guided vehicles is much lower compared to self-driving cars. Automated subway lines can be formalized as a graph. in which the edges are frequented by a ...
1
vote
1answer
30 views

Graph Search Version of A*

I am going through Russel and Norvig's AI A Modern Approach 3rd Edition. I was reading the A* algorithm and it reads A* Graph Search Version is optimal when heuristic is consistent and Tree Search ...
3
votes
1answer
43 views

Is it possible to do K-nearest-neighbours before training DNN

The following X-shape alternated pattern can be separated quite well and super fast by K-nearest Neighbour algorithm (go to http://ml-playground.com to test it): However, DNN seems to face great ...
0
votes
0answers
7 views

Fusing label distribution and on-hot encoded labels

A while ago I came across a paper for image classification that utilized both label distribution and one-hot encoded labels to classify images. An image has a label distribution for all classes (4 ...
0
votes
0answers
58 views

What to do when an image classifier does good for a class but bad for another?

So I wrote a convolutional neural network for a binary image classification. I have around 5300 images for each class which I thought would be enough to at least give me a good accuracy on the ...
1
vote
0answers
23 views

RF: How to deal with environments changing state due to external factors

I have a use case where the state of the environment could change due to random events in between time steps that the agent takes actions. For example, at t1, the agent takes action a1 and is given ...
0
votes
0answers
9 views

What is best dataset for person reidentification?

There are many datasets for person reidentification. I want to train a robust person re-identification neural network. Therefore I want to ask about best person re-identification dataset.
5
votes
0answers
21 views

What is the impact of using multiple BMUs for self-organizing maps?

Sort of a conceptual question here. I was implementing a SOM algorithm to better understand its variations and parameters and got curious about one bit: the BMU (best matching unit == the neuron that ...
1
vote
0answers
13 views

Looking for GAN paper with spiral image

I am looking for a GAN paper I have read a while ago, but unfortunately cannot find it again. I think it compared GANs and other methods (like CVAEs) w.r.t. how they handle multi-modal data, not sure ...
3
votes
1answer
42 views

Can a model, retrained on images classified previously by itself, increase its accuracy?

Let's assume I have a CNN model trained to categorize some objects on the images. By using this model I find more categorized images. If I now retrain this model on data set that consists old set and ...
4
votes
1answer
30 views

dimensions of hidden layer and cell state layer in LSTM

I was following some examples to get familiar with tensorflow LSTM related api, but noticed that all LSTM initialization functions require only num_units parameter which denotes number of hidden units ...
7
votes
1answer
84 views

How does Atlas from Boston Dynamics have human-like movement?

Discussing the video More Parkour Atlas a friend asked how the robot's movement where so similar to the one from a real human and wondering how this is achieve? To my knowledge this is not something ...
2
votes
0answers
26 views

How to transfer learn Darknet YOLOv3

I've started getting into object detection in image. I have YOLOv3 neural network with Darknet framework. The network is pre-trained from COCO data set. Now I need to do some transfer learning in ...
1
vote
0answers
12 views

TD losses are descreasing, but also rewards are decreasing, increasing sigma

I'm using Q-learning with some extensions such as noisy linear layers, n-steps and double DQN. The training, however, isn't that successful, my rewards are descreasing over time after a steep ...
9
votes
0answers
59 views

Will parameter sweeping on one split of data followed by cross validation discover the right hyperparameters?

Let's call our dataset splits train/test/evaluate. We're in a situation where we require months of data so we prefer to use the evaluation dataset as infrequently as possible to avoid polluting our ...
3
votes
1answer
45 views

Terminology for the use of datasets as data points

As computers are getting bigger better and faster, the concept of what constitutes a single datum is changing. For example, in the world of pen-and-paper, we might take readings of temperature over ...
5
votes
1answer
33 views

Is the agent aware of a possible different set of actions for each state?

I have a use case where the set of actions is different for different states. Is the agent aware of what actions are valid for which states or is the agent only aware of the entire action space (in ...
3
votes
0answers
22 views

Vector normalization by a neural network

I'm wondering if there is a NN that can achieve the following task: Output a unit vector that is parallel to the input vector. i.e., input a vector $\mathbf{v}\in\mathbb{R}^d$, output $\mathbf{v}/\|\...
4
votes
1answer
43 views

How to deal with large (or NaN) neural network's weights?

My weights go from being between 0 and 1 at initialisation to exploding into the tens of thousands in the next iteration. In the 3rd iteration they become so large that only arrays of nan values are ...
3
votes
1answer
32 views

GPU/TPU acceleration for neural networks with various network topologies

I was thinking about different neural network topologies for some applications. However, I am not sure how this would affect the efficiency of hardware acceleration using GPU/TPU/some other chip. If, ...
11
votes
1answer
176 views

What are all the different kinds of neural networks used for?

I found the following neural network cheat sheet (Cheat Sheets for AI, Neural Networks, Machine Learning, Deep Learning & Big Data). What are all these different kinds of neural networks used ...
4
votes
3answers
109 views

Is randomness necessary for AI?

Is randomness (either true randomness or simulated randomness) necessary for AI? If true, does it mean "intelligence comes from randomness"? If not, can a robot lacking the ability to generate random ...
3
votes
1answer
40 views

Puzzle solving AI?

I have a book containing lots of puzzles with instructions like: ...
3
votes
2answers
97 views

What kind of neural network architecture is suitable for variable length block-like time series data?

I'm not sure what this type of data is called, so I will give an example of the type of data I am working with: A city records its inflow and outflow of different types of vehicles every hour. More ...
0
votes
0answers
7 views

How is Average Recall (AR) calculated for an object detection model?

After looking around the internet (including this paper, I cannot seem to find a satisfactory explanation of the Average Recall (AR) metric. On the COCO website, it describes AR as: "the maximum ...
0
votes
0answers
13 views

Predict the next best action based on previous lists of actions

I have the following problem. There is a software that I've written some time ago. Users enter customer's data in the system and there is a limited number of things (actions) that they can do/add - ...
5
votes
1answer
33 views

How can we conclude that an optimization algorithm is better than another one

When we test a new optimization algorithm, what the process that we need to do?For example, do we need to run the algorithm several times, and pick a best performance,i.e., in terms of accuracy, f1 ...
0
votes
0answers
17 views

Better versions of LSTM

I know recurrent neural networks for example LSTM is one of them. After LSTM different variants of LSTM have come for example GRU. I don't know about newer RNN like LSTM and GRU, so I decided to ask ...
1
vote
0answers
31 views

Is there a GAN that can be used for sequence prediction?

I want to use a GAN for sequence prediction, in a similar way that we use RNNs for sequence prediction. I want to test its performance in comparison with RNNs. Is there a GAN that can be used for ...
0
votes
0answers
9 views

what is the best dataset (or combination of datasets) for training a person detector?

I want to train a person detector for MOTChallenge dataset, but I want to avoid using the dataset as training set for my detector. Therefore, I want to use another dataset or combination of several ...
2
votes
1answer
30 views

What sort of Neural Network is best suited to predicting a future purchase?

I have previously implemented a Neural Network with Back-Propagation that was able to learn Tic-tac-toe and could go pretty well at Connect-4. Now I'm trying to do a NN that can make a prediction. ...
-1
votes
0answers
48 views

Is My Formula For a Neural Network correct?

I am creating a multi-layer neuron library in C# and doubtful of my understanding of neural network correctness as my answer even after the training of xor is always nearer 0.5. Here are the notation ...
0
votes
0answers
16 views

DQN unlearns certain OpenAI-Gym environments

I solved the OpenAI-Gym MountainCar-v0 environment using dqn(using low-state-dimensional input). When I used the same code for solving CartPole-v0 environment, the network got trained in the reverse ...
0
votes
1answer
30 views

How would an AI understand grids?

OK, now I think an AI must view grids in a different way to computers. For example a computer would represent a grid like this: ...
0
votes
0answers
22 views

Formal definition of a “non-local” game?

This is an area I'm just getting into and starting to review the literature, but I can't easily find a fundamental definition of "nonlocal game". I came across the term in reference to methods of ...
0
votes
1answer
19 views

How to change this RNN text classification code to become text generation code?

I can do text classification with RNN, in which the last output of RNN (rnn_outputs[-1]) is used to matmul with output layer weight and plus bias. That is getting a word (class name) after the last T ...
2
votes
0answers
29 views

Algorithm to solve a fault independent of its type

I am looking to plan a solution for a workspace fault and not hardware faults. Consider a task where a robot has to move balls from one place to another. In case it faces any condition which is ...

15 30 50 per page