All Questions

Filter by
Sorted by
Tagged with
2
votes
1answer
45 views

What happens to the optimal value function if the reward is multiplied by a constant?

What happens to the optimal action-value function, $q_*$ if the reward is multiplied by a constant $c$? Is the optimal action-value function also multiplied by such a constant?
4
votes
1answer
63 views

How do we determine whether a heuristic is better than another?

I am trying to solve a Maze puzzle using the A* algorithm. I am trying to analyze the algorithm based on different applicable heuristics. Currently, I explored the Manhattan and Euclidean distances. ...
1
vote
0answers
21 views

Threshold selection for Siamese network hyper-parameter tuning

I'm interested in modeling a Siamese network for facial verification. I've already written a simple working model that inputs feature vectors generated from two CNNs with shared weights then outputs a ...
-1
votes
0answers
33 views

Which opinions are available to slow down the DexNet robotic grasping project?

The first version of a robotic arm who is able to grasp objects dexterously was announced three years ago. [1] It is working with convolutional neural networks who are trained on thousands of 3d ...
1
vote
0answers
15 views

Clustering of very high dimensional data and large number of examples without losing info in dimensions

I'm trying to get a grasp on scalability of clustering algorithms, and have a toy example in mind. Let's say I have around a million or so songs from $50$ genres. Each song has characteristics - some ...
1
vote
0answers
28 views

Can existing cognitive services be used for name and gender recognition in a story?

Can I use any of the existing cognitive services from Microsoft, IBM or AWS to recognize the name and gender of characters (actors) from a story (novel) book (written in plain text or pdf format)?
3
votes
1answer
22 views

Image classification with an associated matrix

I have a dataset of images with 9 different classes. However, there are different categories with the same type of associated image and only can be differentiated with an associated matrix in my ...
3
votes
0answers
19 views

Handwritten digits recognition during the process of writing

I know how to train a NN for recognizing handwritten digits (e.g. using the MNIST database). I'm wondering how to accomplish the same "online", which is during the process of writing e.g. I'm writing ...
2
votes
1answer
62 views

Monte Carlo learning for Reinforcement learning

When you train a model using Monte Carlo-based learning the state and action taken at each step is recorded, and then at some point an end state is reached and the agent receives some reward - what do ...
-2
votes
1answer
45 views

Python ERROR: No matching distribution found for tensorflow [closed]

Now as I understand that kind of technical questions is out of scope for the ai.stackexchange.com I will use stackexchange.com for such technical questions. Thank you for you all for your ...
1
vote
2answers
36 views

How to express accuracy of a regression ANN that uses MSE loss function?

I have a regression MLP network with all input values between 0 and 1, and am using MSE for the loss function. The minimum MSE over the validation sample set comes to 0.019. So how to express the '...
-3
votes
1answer
57 views

Can a random generator become the social role of an AI?

The following Python script is used to produce the movements of a game AI character in a videogame. ...
2
votes
1answer
47 views

Can an RL algorithm trained in one environment be successful in a different one?

Can an RL algorithm trained in one environment be successful in a different one? For example, if I train a model to go through one labyrinth, could this model also go through a different but similar ...
2
votes
2answers
33 views

What are criteria for ML model to be satisfactory for commercial use?

I often read "the performance of the system is satisfactory" or " when your model is satisfactory". But what does it mean in the context of Machine Learning? Are there any clear and/or generic ...
0
votes
0answers
18 views

Improving Recall of a Certain Class

Let's say that we have a test data set with $20,000$ observations for which we want to make a binary prediction for. When we apply our best trained model to this data set (e.g. logistic regression ...
1
vote
0answers
12 views

CBIR Evaluation on contextually different data

How good would a CBIR system trained on a dataset, for example, DELF, trained on the Google Landmarks dataset, perform when evaluated on a contextually different dataset such as the WANG or the COREL ...
3
votes
1answer
109 views

Why isn't my Neural Network based calculator working?

I am playing around with neural networks in Tensorflow and I figured an interesting test would be whether I can write a calculator using a Tensorflow Neural Network. I started with simple addition ...
2
votes
2answers
41 views

Can ML be used to curve fit data based on dataset of example fits?

Say I have x,y data connected by a function with some additional parameters (a,b,c): $$ y = f(x ; a, b, c) $$ Now given a set of data points (x and y) I want to determine a,b,c. If I know the model ...
1
vote
1answer
30 views

How well can ConvNET distinguish an object from its class?

ConvNET can easily predict class of an object in an image. My question is, can ConvNET distinguish Pisa Tower from other buildings or Hagia Sophia from other mosquoes easily? If it can, how many ...
0
votes
1answer
62 views

How can the derivative of a neural network be calculated, given no mathematical expression?

Neural networks (NNs) are used as approximators in reinforcement learning (RL). To update the policy in RL, the actor network's gradients w.r.t its weights are needed. Since NN doesn't have a ...
0
votes
1answer
30 views

Maximum Likelihood Classifier vs. Bayesian Network

I am confused in understanding the Maximum Likelihood as a classifier. I know what is Bayesian network and I know that ML is used for estimating the parameters of models. Also, I read that there are ...
0
votes
1answer
32 views

Network doesn't converge with ReLU or Leaky ReLU, but works well with sigmoid/tanh

I have these training data to separate, the classes are rather randomly scattered: My first attempt was using tf.nn.relu activation function, but output was stuck ...
0
votes
1answer
25 views

is a “word prediction” problem, applicable using HMMs?

I'm learning HMMs and decided to model a problem for learning purposes. I came to this idea of word predicting by letters. here is the model : while typing, the word is typed letter by letter, so we ...
5
votes
1answer
34 views

Reinforcement learning with incremental action space

Let's say we have a problem which can be solved by some RL algorithms (DQN, for example, because we have discrete action space). At first, the action space is fixed (the number of actions is $n_1$), ...
1
vote
0answers
28 views

Indian Traffic Sign Dataset

I am looking for the Indian Dataset of traffic signs. There is a dataset developed recently IDD: A Dataset for Exploring Problems of Autonomous Navigation in Unconstrained Environments which contains ...
0
votes
0answers
14 views

Probabilistic classification - normalize results

I have a probabilistic classifier that produces a distribution over my 3 classes - C1, C2, C3. I want to compare some new points I'm classifying to each other, to see which one is the best fit for a ...
1
vote
1answer
31 views

How is the actor-critic algorithm guaranteed to converge?

From my understanding, the critic evaluates the policy (actor) following dynamic programming (DP) or approximate dynamic programming (ADP) scheme, which should converge to the optimal value function ...
4
votes
2answers
75 views

AI on Academic vs Industry vs Competition

When we are working on an AI project, does the background or the domain make the process different? The "domain" I mean here is like AI for academic research, AI for industry, and AI for competition. ...
0
votes
0answers
15 views

Why do both sin and cos have been used in positional encoding in Transformer model?

The Transformer model proposed in "Attention Is All You Need" uses sinusoid functions to do positional encoding. I wonder why do both sin and cos been involved in? And why do need to separate the odd ...
1
vote
0answers
50 views

Is Value Iteration better than Policy Iteration for first few iterations?

In Policy Iteration (PI), the action generated by the policy, whether it's optimal or not w.r.t the current value function $v(s)$. Whereas, in Value Iteration, the action is greedily generated w.r.t ...
1
vote
1answer
29 views

Can policy iteration use only the immediate reward for updates?

Is it still a policy iteration algorithm if the policy is updated optimizing a function of the immediate reward instead of the value function?
-1
votes
1answer
36 views

How to calculate the false positives and negatives?

I have a huge amount of data and I want to calculate my false positive and false negative. Is there a software that can help me determine it?
1
vote
0answers
30 views

why the sigmoid function will be 1 and 0 if we use a fully connected layer that produce a big enough positive(res negative )output

HI I am using a fully connected network that uses sigmoid if we feed a a big enough weights the sigmoid function will finally become 1 or 0 , is there any solution to avoid this ? and will this lead ...
3
votes
1answer
32 views

How important is the choice of the initial state?

Is it crucial to always have the same initial (starting) state for Reinforcement Learning, for example, for Q-learning or DQN? Or it can vary?
0
votes
0answers
14 views

Matterport MRCNN and multiclass classification

I want to create a model which solve a multiclass classification problem. The main concept is: every picture contain only one object the background is very simple all object is coming from the same ...
0
votes
0answers
6 views

Object detector always predict high confidence bounding box after dataset augmentation

I am using the Object Detection API to train a MobilenetV2-SSD object detector with just one class. I started from the sample pipeline tuned for the COCO dataset. During the first training I could ...
0
votes
2answers
22 views

Is it still called linear separation with a layer of more than 1 neuron

A single neuron will be able to do linear separation. For example, XOR simulator network: ...
3
votes
1answer
51 views

Advantages of Kullback-Leibler over L1/L2?

I've recently encounter different articles that are recommending to use KL instead of L1/L2 norm when trying to minimize a probability distribution. But none of the articles are giving a clear ...
0
votes
0answers
38 views

Can neural networks output the rules it is using?

I have made a neural network using TensorFlow that is able to identify IP addresses that are likely to have a vulnerability of type A. I want to output the rule it has made for this identification.
3
votes
1answer
54 views

What is a non-starving policy in reinforcement learning?

In the paper, Eligibility Traces for off-Policy Policy Evaluation (2010), by Doina Precup et al., mentioned the term "non-starving" many times. The specific use of the term was like "non-starving ...
1
vote
1answer
61 views

Is it worth getting a masters in AI from a top 100 ranked university?

I’ve heard it’s not worth getting a masters from a school that’s not top 100, but AI masters is not that common so I feel the selection is quite scarce. Is it worth getting a masters in AI from not a ...
1
vote
0answers
16 views

Which AI algorithm is great for mapping between two XML files

My work colleague got a project with a lot of work that is not hard or complicated. The problem is simple but it is a lot of work. We have two XML files with a lot of variables in it. Not only is ...
1
vote
2answers
61 views

What kind of experience do I need to get into an AI master's programme?

I'm about to go into my third and final year of my mathematics degree and I recently discovered some master's programmes in AI that really interest me. I have very little experience in programming. I'...
3
votes
1answer
31 views

Reinforcement learning with hints or reference model

In Reinforcement Learning, when I train a model, it comes up with its own set of solutions. For example, if I am training a robot to walk, it will come up with its own walking gait, such as this Deep ...
0
votes
0answers
14 views

Invalid moves in Deep Reinforcement Learning for games [duplicate]

I've been working on a bot for a game involving dice throws and chance. The architecture involved is similar to AlphaZero in the that it has Convolutions and MCTS. According to the current state ...
1
vote
0answers
41 views

Why humans aren't motivated to play robot games? [closed]

The screenshot shows a prototype of a robot simulator. It's a robotarm in a physics simulation which can be controlled manual by the slider in the GUI. The idea is, that the human sets a value and ...
1
vote
0answers
27 views

I am trying to create a network with dynamic connections for every different training example

I have developed a new algorithm which has dynamic connections. it is based off of the following paper: https://www.researchgate.net/publication/...
0
votes
1answer
38 views

How many hidden layers are needed for this training data set

I'm trying to separate classes in 3D space, the data are as in the sketch below: There are 3 classes: 0,1,2; and with the look into the sketch, it seems that I need 3 planes to separate the classes, ...
0
votes
0answers
10 views

Is there any reason to believe a ml pipeline that works on dataset A will work on dataset B where both have similar meta features?

I’m working on generating an automl pipeline(a combination of data cleaning and transformation algorithms applied to a dataset then generate a model) that works on a new dataset by looking for past ...
2
votes
0answers
21 views

Can two neural networks be better instead of one with a categorical feature?

Let's assume, that I have a neural network with few numerical features and one binary categorical feature. The network in this case is used for regression. I wonder if such a neural network can ...

15 30 50 per page