Questions tagged [ai]

AI (Artificial Intelligence) is a branch of computer science concerned with creating human-like intelligence in machines (including perception, learning, problem solving and decision making).

Filter by
Sorted by
Tagged with
3
votes
1answer
51 views

Convolutional neural network low performance

Problem description I'm doing Signal Modulation Classification using a Convolutional Neural Network, but performances are very low (around 15% accuracy) and I can't find out why. Data Dataset is ...
0
votes
0answers
14 views

Qaulity assurance framework for ML/AI

I'd like to hear how organisations are applying a quality framework to ML/AI work. I'm struggling to find good content or good practice on this. By saying quality frameworks, for example, if I was ...
0
votes
0answers
54 views

Did DeepBlue use machine learning?

Did IBM's DeepBlue, which defeated a human player in chess in 1997, use machine learning? I am a bit confused by this article that says that it is AI, but not ML. Whereas this article says it is AI ...
0
votes
0answers
17 views

what is convolutional implementation of sliding window in Faster RCNN? Also how RPN proposes region?

do we need to train this model on some standard dataset separately? and then use it? can we use pre trained model such as VGG etc for this? also How RPN is used to propose regions?? unlike ...
1
vote
0answers
28 views

Backpropagation on a CNN

I have tried searching for this, but it seems like no one addresses a key aspect of this problem (or maybe I'm overthinking this): So, first let's assume we have a 3x3 image with a single channel, and ...
1
vote
0answers
55 views

Machine learning algorithms for suggesting new baby names [closed]

https://www.lexalytics.com/lexablog/machine-learning-natural-language-processing https://towardsdatascience.com/named-entity-recognition-ner-meeting-industrys-requirement-by-applying-state-of-the-art-...
0
votes
0answers
17 views

ADAM optimizer yields sub-optimal results

I've been writing my own neural network from scratch to get a better understanding of how they work (using MATLAB initially, but plan to port it to C++ afterwards). One major problem for me has been ...
2
votes
1answer
36 views

Machine Learning - Euclidian Distance Classifier exercise [closed]

I'm taking part in an elective subject at university which mainly focuses on the foundations of Machine Learning. Now we got our first exercise - this task should be done practically in any language (...
1
vote
1answer
27 views

I'm planning to record video now and then analyze it in the future once AI programs are more accurate, what resolution and FPS should I record at? [closed]

I'm going to record videos and want to future proof them for AI analysis as much as possible. I have a decent amount of storage to work with, 2.7TB. I'm hoping to make it last for at least two years. ...
1
vote
1answer
30 views

what does one Shot learning mean? do they only need one image to train for some new class detection?

Being new to deep learning I am somewhat struggling to grasp the idea of one shot learning. Let us say I have a class to detect which didn't exist in training dataset such as COCO or Image NET. Can I ...
2
votes
0answers
25 views

"Learning" algorithm to use when future depends on past events (MDP property not met)

There are around 5 different retirement plans available in my country. People can pick from them freely. I would like to create a solution that would try to predict the best plan(s) given a particular ...
0
votes
0answers
9 views

How to make Training Data for Meta-Learning

If I am doing 5-way-1-shot meta learning on dataset with 200 classes, what would be the sample space for my labels? I know there would be 5 labels in each meta-set, but will I be chosing labels from ...
0
votes
1answer
57 views

Difference between $Q(s,a)$ ,$V^*(s)$ and $V^\pi(s)$ in Markov Decision Process?

I am new to RL and I am trying to understand how to find solutions of an MDP. This is what I understand so far -> since the nature of our environment is stochastic, at a state 's' if we take an ...
0
votes
1answer
28 views

Word2Vec: Identifying many-to-one relationships between words

Standard introductory examples in Word2Vec, like king - queen = man - woman and tokyo - japan = london - uk, involve one-to-one ...
1
vote
1answer
112 views

Need help with prolog program

I am new to prolog and need help on how to write a prolog program. Here is what i am trying to do. I have downloaded the dataset from this link - https://archive.ics.uci.edu/ml/datasets/Blood+...
0
votes
1answer
34 views

How to grade an interaction that a user had with a post with an AI based on big data?

Context I'm creating a social network. The thing is, I don't want to order posts by likes, or something like that, I'm using an AI (lightfm in ...
1
vote
1answer
16 views

How many run should we implement on the machine learning model?

Theoretically, we can implement fix seed on the machine learning model to get the same results every run (reproducible)but it may leads to bias. So, in order to prevent bias, I gonna run the model ...
0
votes
0answers
21 views

I think a learning rate schedule would be counter-productive with AdaBelief. Am I wrong?

I am inclined to believe the concept of a learning rate schedule is overcome by the improvements of Adabelief over Adam. My code is on Github; please check it out and attempt to replicate my results, ...
0
votes
1answer
29 views

Emotion detection on audio

I'm trying to apply emotion detection on audio. Basically, given an audio file, it must generate emotional labels for a segment of any durations, say every 5s chunks, like happy, sad, angry, etc. Is ...
-1
votes
1answer
43 views

Machine learning, speech recognition technologies for Sound of Animals interpretation [closed]

https://www.google.com/search?q=sound+of+animals&client=ms-android-lava&prmd=inv&sxsrf=ALeKk02xrn0-yn-FZSkidTogB4l4B_TH6A:1600539091086&source=lnms&tbm=isch&sa=X&ved=...
0
votes
0answers
37 views

What is the algorithm/logic top e-commerce companies use to show products in "What's new?" and "Bestsellers" sections on the website?

I am trying to solve this problem for a fashion e-commerce website that sells t-shirts, joggers etc. Till now I am only able to make some rule based logics only. It looks something like this The ...
3
votes
0answers
46 views

Could my AI classifier be extended to categorical data? [closed]

I created a new AI classifier. Physics Based Classifier
0
votes
2answers
131 views

Stamps detection using AI, Computer vision & Machine Learning technologies

https://en.wikipedia.org/wiki/Postage_stamp https://www.google.com/search?q=stamps&client=ms-android-lava&prmd=isnv&sxsrf=ALeKk02Ik_sWwymBctdONPasm7w0YNXcZA:1599240889888&source=lnms&...
2
votes
3answers
213 views

Significance of Object-Oriented Programming (OOP) in Data Science [closed]

Can someone please explain to me the role of Object-Oriented Programming (OOP) and Object-Oriented Design (OOD) in Data Science? I am from a non-computer science background. Do I need to learn these ...
2
votes
1answer
82 views

What is semantic gap? Why it exists in AI

The semantic gap characterizes the difference between two descriptions of an object by different linguistic representations, for instance languages or symbols. The semantic gap can be defined as "...
0
votes
1answer
34 views

Machine Learning algorithm for predicting number of cases in pandemic

I’m giving my first steps with AI and Machine Learning so I have the following issue. I’m trying to predict an outcome from COVID-19 number of day vs confirmed cases using scikit-learn library. I mean,...
0
votes
1answer
58 views

Will the job of Data Science is going to be at risk? [closed]

Data Science is the sexiest job of 21st Century according to the different sources with a high payment salary . But it seems that there will be over production of this profession . According to U.S. ...
1
vote
0answers
41 views

Why the validation accuracy does not increase in a normal way over the epochs?

I'm trying to transfer learning VGG16 model with imagenet in a dataset of retinal images but i'm confused to get a graph like this in the picture below, I don't know why the validation accuracy didn't ...
2
votes
1answer
41 views

Call routing using AI

I'm trying to find out how AI can help with efficient customer service, in fact call routing to the right agent. My usecase is given context of a query from a customer and agents' expertise, how can ...
2
votes
1answer
109 views

How to generalize comments using NLP

I have list of log comments in CSV file. I want to cluster those log comments using K-Means and after that I want convert each cluster comments into general form. for eg. I have bunch of comments in ...
3
votes
2answers
52 views

How to generate a sentence with exactly N words?

Thanks to GPT2 pretrained model now it is possible to generate meaningful sequence of words with or without prefix. However a sentence should end with a proper endings (.,!,?). I am just wondering how ...
1
vote
1answer
114 views

Convolutional neural network giving high confidence on wrong classification

I am doing a project on sign language recognition through CNN. My Dataset 300 images for each alphabet and one special symbol for space. Images are taken from three individuals. Each image has hand ...
1
vote
1answer
674 views

Deep learning based Resume Parser and Scoring

I want to know if Deep learning can be used for Resume Parsing and scoring of the resume. Currently what I am doing is extracting the text from pdf or image using OCR/tesseract and finding the ...
1
vote
0answers
24 views

RESOURCE EXHAUSTED error with Kfold on a facial landmarks data

i am currently working with helen dataset to predict facial landmarks. Currently running the program on a Geforce 1070. The highest batch size i can give is 230 and i am getting a loss of 3 and ...
3
votes
2answers
903 views

What does scaling a gradient do?

In the MuZero paper pseudocode, they have the following line of code: hidden_state = tf.scale_gradient(hidden_state, 0.5) What does this do? Why is it there? I'...
1
vote
3answers
80 views

Data science which is not part of AI?

I have understood that data science is part of AI. However, do we have some area in data science which we can say does not fall under AI? If yes, please name them.
1
vote
0answers
26 views

Rewards are converged but with a lot of variations

I am training a reinforcement learning agent on an episodic task of fixed episode length. I am tracking the training process by plotting the cumulative rewards over an episode. I am using tensorboard ...
1
vote
1answer
101 views

Having a reward structure which gives high positive rewards compared to the negative rewards

I am training an RL agent using PPO algorithm for a control problem. The objective of the agent is to maintain temperature in a room. It is an episodic task with episode length of 9 hrs and step size(...
1
vote
1answer
47 views

Formulation of a reward structure

I am new to reinforcement learning and experimenting with training of RL agents. I have a doubt about reward formulation, from a given state if a agent takes a good action i give a positive reward, ...
0
votes
2answers
72 views

Neural network is not giving the expected output after training in Python

My neural network is not giving the expected output after training in Python. Is there any error in the code? Is there any way to reduce the mean squared error (MSE)? I tried to train (Run the ...
0
votes
1answer
58 views

How to handle differences between training and deploying of an RL agent

Hi I am training an RL agent for a control problem. The objective of the agent is to maintain temperature in a zone. It is an episodic task with episode length of 10 hrs and actions being taken every ...
4
votes
1answer
621 views

Can AI (NLP) convert user questions (text) into database SQL queries?

I have been reading about NLP but got confused and not able to figure out - if it is feasible for NLP to convert questions in natural language to transform into SQL queries (so that it can execute on ...
1
vote
1answer
2k views

Policy Gradient with continuous action space

How to apply reinforce/policy-gradient algorithms for continuous action space. I have learnt that one of the advantages of policy gradients is , it is applicable for continuous action space. One way I ...
1
vote
0answers
27 views

Can linear classifiers be used at each node of a decision tree instead of the lines parallel to any one of the axes?

I am relatively new to AI/ML. I came across this question while reading some content on ML. Would be of great help if anyone can answer this
0
votes
1answer
49 views

Reward is converging but actions taken by trained agent are illogical in reinforcement learning

I am training a reinforcement learning agent using DQN. My state space has 6 variables and the agent can one action which is discretized into 500 actions My reward structure looks like ...
0
votes
2answers
387 views

How to calculate Temperature variable in softmax(boltzmann) exploration

Hi I am developing a reinforcement learning agent for a continous state/discrete action space. I am trying to use boltmzann/softmax exploration as action selection strategy. My action space is of size ...
1
vote
0answers
38 views

temperature variable in boltzmmann-exploration in reinforcement learning

I have been using epsilon greedy action selection strategy and recently have come across boltzmann(softmax) action selection strategy. One thing I am not clear about boltzmann exploration is the ...
2
votes
0answers
521 views

TensorFlow and Keras models having same parameters, hyperparameters, weights and bias initialization giving different accuracy

I have made sure that layers, parameters, hyperparameters, kernel_initialization, bias_initialization, seeds and datasets are all equal. But still the output for both the models are different. ...
1
vote
2answers
720 views

RandomForest surprisingly high accuracy

I've been experimenting with Random Forests on Python after trying Naive Bayes which gave me lower accuracy than I expected, 62%. My csv file has around 14,000 records, I use 80% for the training set ...
0
votes
2answers
52 views

Does an RL agent learn during exploitation?

I have started with RL and have some doubts regarding it. Does an RL agent learn during exploitation, or does it only learn during exploration? Is it possible to train a model only using exploitation ...