6
votes
Is it necessary to know the details behind the AI algorithms and models?
This is a good question. I tend to think the answer is yes it is necessary to know the details, because a person without mathematical understanding of these algorithms cannot consistently make a model ...
5
votes
Accepted
What are the most challenging tasks aiming to achieve the lowest error rate?
Yes. Here are some of the most prominent ones and their respective state-of-the-art errors:
CIFAR-10: ~3.5% error
CIFAR-100: ~24% error
STL-10: ~26% error
SVHN: ~1.7% error
ImageNet tasks: the best ...
4
votes
Accepted
Musical notes interpretation
AI/ML can solve the task described, a solution is as below:
Regular image processing algorithm (pixel row with min black pixels, adjacent rows are considered as 1) to split the sheet music (as image) ...
4
votes
How to implement exploration function and learning rate in Q Learning
Your main problem is that you need to separate out what is driving the behaviour policy from the Q-table.
Q Learning is an off-policy algorithm. The Q-table that it eventually learns is for an optimal ...
4
votes
What should we do when we have equal observations with different labels?
The problem you are portraying looks like a modified XOR problem. You can't throw away the lines with a label of 1 because a the model won't be able to learn this class.
4
votes
What is the relationship between data science, artificial intelligence,machine learning and computer vision?
This Venn diagram might help to visualize the relation between the different fields:
The image is from the free deep learning book by Ian Goodfellow, Yoshua Bengio and Aaron Courville. As you said ...
4
votes
What is a pipeline in machine learning?
A data pipeline consists of 3 main steps
data collection (e.g. you collect images of cats from different sources)
data transformation (e.g. you make the images all have the same dimensions and maybe ...
3
votes
What is a pipeline in machine learning?
A "pipeline" typically refers to a chain of methods where the output of the one is used as the input of another method.
This could be, e.g., a "preprocessing pipeline" where ...
2
votes
Accepted
How to rescale data to its original range after MinMaxScaler?
You can use the function inverse_transform of the created MinMaxScaler object.
See also this Stack Overflow question for other ...
2
votes
Accepted
How do I know if my dataset is ready for a machine learning model?
Before jumping to modeling, there are a few tasks a data scientist (or ML/AI practitioner) must do:
Ideation (or hypothesizing): Before applying any modeling approach, we need to ask the right ...
2
votes
Accepted
What data formats/pipelining are best to store and wrangle data which contains both text and float vectors?
There are different possible ways to handle huge datasets:
If the data is too big to be fully uploaded to RAM, you can iterate over it in Pandas. You can find a brief explanation in the article ...
2
votes
Accepted
How to define the "Pre-Processing" in machine learning?
Data preprocessing consists of all those techniques used to generate the final datasets (with an appropriate size, structure, and format) for the machine learning algorithms or models. Data ...
2
votes
Is this dataset with only two features suitable for clustering with k-means?
One problem with clustering algorithms is that they will typically find you a solution, ie they will split your data set into clusters, but it will find you a structure even if there isn't one. Your ...
2
votes
Accepted
How can I address missing values for LSTM?
You can claim to use a real-world dataset, you would just need to specify that some values were interpolated.
Do you have to have the inter-mediate values though? By the looks of it, each "region&...
2
votes
Accepted
How to tackle the human error made in labeling datasets for classification tasks like facial expression recognition?
In general the only way to deal with this is by quantifying these labeling mistakes in the output of the model, since the model will learn for them. And in many cases these are not really mistakes, ...
2
votes
Musical notes interpretation
LMGTFY ;)
The problem is called Optical Music Recognition. Here you can find tutorial that desribes OMR with deep learning and here you have scientific paper. I think it is very good start for your ...
1
vote
Accepted
Generating a dataset from data with "assumed" lables
I think you need to look into semi-supervised learning, which combines supervised and unsupervised learning for problems where large labelled datasets are not available. To use this family of ...
1
vote
Is there a clustering algorithm that can make n clusters and the n+1 "others" cluster?
So, I've prepared some data that resembles your sketch:
...
1
vote
Predicting a day's data
Just for clarification: your description (1 sample per minute) does not match the example data (far fewer data points which is understandable, but also two data points in one minute which contradicts ...
1
vote
Accepted
Can alpha-beta pruning be used for applications apart from games?
Thinking about this more, the answer is in fact yes, but not for the application you mention.
You cannot use alpha-beta pruning to learn a model to predict customer outcomes, because it is only ...
1
vote
How to calculate the false positives and negatives?
Yes, you can use sklearn's confusion_matrix. To explicitly extract the false positives and negatives, you can do
...
1
vote
What should we do when we have equal observations with different labels?
This is perfectly acceptable in a stochastic environment. Generally your loss is to minimize $-log\ p(Y|X)$ or equivalently $-\sum_i log\ p(y_i|x_i)$. This optimization is equivalent to $-\mathbb{E}\...
1
vote
Automatic prediction of whether a customer will come into the shop or not
This should be possible, but it's not completely clear what you are trying to do.
If you're trying to predict customer age and gender from a video, then you've got a computer vision problem. Deep ...
1
vote
multi vs one prediction using Regression
I think the model will have no problem taking a multicolumn input. In fact, from your code, this is exactly how you trained it. It expects an input of size [k, 6], where k is k>=1.
Instead you are ...
1
vote
What types of machine learning model would fit?
Welcome to AI.SE @Par!
What you have might be either a multi-label or a multi-class classification problem. If the classes are disjoint (each example belongs to just 1 of the 50 classes), it's a ...
1
vote
Loss/accuracy on Synthetic data
No, there is no difference.
Of course, you are likely not able to extrapolate results obtained from synthetic data to expect identical or similar results in real life to unless you have very ...
1
vote
Accepted
Parameters to calculate affluence in localities of Metro city
Affluence could encompass several parameters:
Income;
Wealth (property ownership);
Life expectancy;
Access to services such as education and health;
Access to clean natural resources;
Low levels of ...
1
vote
Accepted
Which field to study to learn & create a.i generated simulations?
You need to define "simulation" more specific. Playing Mario, Swapping face on image/video, or generating simulation of objects that are orbiting use different techniques.
Playing Mario or "AI that ...
1
vote
Accepted
Help with Novelty Recognition and Binary Classification for Emotion Recognition
The Project
It appears from the question that emotional detection and response is the longer term goal of the project and that recognizing potential emotional manifestations in easily detectable ...
1
vote
What is the impact of scaling the features on the performance of the model?
In general, algorithms that exploit distances or similarities (e.g. in the form of scalar product) between data samples, such as k-NN and SVM, are sensitive to feature transformations. We do feature ...
Only top scored, non community-wiki answers of a minimum length are eligible
Related Tags
data-science × 60machine-learning × 28
data-preprocessing × 12
deep-learning × 11
datasets × 9
neural-networks × 6
python × 4
image-processing × 4
natural-language-processing × 3
tensorflow × 3
keras × 3
prediction × 3
unsupervised-learning × 3
clustering × 3
data-labelling × 3
data-mining × 3
reinforcement-learning × 2
convolutional-neural-networks × 2
terminology × 2
ai-design × 2
image-recognition × 2
long-short-term-memory × 2
statistical-ai × 2
academia × 2
accuracy × 2