Skip to main content
7 votes
Accepted

Training a classifier when some of the features are unknown

Welcome to Data Science SE! Well, we say that most of our jobs is to wrangle with data, and that is because data is usually trying to deceive us... jokes aside: You have a missing data problem that ...
Pedro Henrique Monforte's user avatar
6 votes
Accepted

Using the cosine activation function seems to perform very badly

Cosine is not a commonly used activation function. Looking at the Wikipedia page describing common activation functions, it is not listed. And one of the desirable properties of activation functions ...
Neil Slater's user avatar
5 votes
Accepted

Performance and architecture of neural network for increased dimensions

Some things to take into account: Try to apply appropriate input space transformations, e.g. convert to polar coordinates. Despite the fact that a single hidden layer feedforward network can be a ...
noe's user avatar
  • 27k
5 votes
Accepted

Is there a problem of over fitting in my dataset?

It is not possible to tell whether a machine learning algorithm is overfitting based purely on the training set accuracy. You could be right, that using more features with a small data set increases ...
Neil Slater's user avatar
5 votes
Accepted

How to make sense of confusion matrix

Adding to the answer above, The labeling totally depends on how you define it. You can define 0 as negative or as positive. However, for the sake of understanding and ease of readability, keep it ...
aathiraks's user avatar
  • 704
5 votes
Accepted

Data Visualization with multiple dimension, and linear separability

You basically need a t-SNE plot, the t-SNE will convert the high dimensional feature vector (several features in your case) to a 2d point and then you can use matplotlib to plot, while plotting you ...
William Scott's user avatar
5 votes

Data Visualization with multiple dimension, and linear separability

When class labels are known, you can use Linear Discriminant Analysis (LDA) for visualization to see whether classes are linearly separable. LDA is similar to PCA but supervised. It tries to project ...
Esmailian's user avatar
  • 9,352
4 votes
Accepted

Avoid reloading DataFrame between different python kernels

If it's important for your use cases, you could try switching to Apache Zeppelin. As all Spark notebooks there share the same Spark context, same Python running environment. https://zeppelin.apache....
Tagar's user avatar
  • 198
4 votes

K-Fold Cross validation confusion?

The accuracy is different because there are k-classifiers made for each number of k-folds, and a new accuracy is found. You don't select a fold yourself. K-Fold cross-validation is used to test ...
Eric C. Bohn's user avatar
4 votes
Accepted

Can we implement random forest using fitctree in matlab?

I would highly recommend doing some research into the architecture of random forests. There are many sites that provide in depth tutorials on RFs (Implementation in Python). Quick explanation: take ...
Hobbes's user avatar
  • 1,459
4 votes

Tuning C hyper parameter in Soft Margin SVM in Matlab

The easiest way to tune a single hyperparameter is to use what is called the elbow method. Do the following: Define a range of C you want to try, i.e ...
Simon Larsson's user avatar
3 votes

How do you calculate Precision and Recall using a confusion matrix in Matlab?

if yHat are your predictions and yval are your y true then ...
Martin Forte's user avatar
3 votes

How do I compare traditional classifiers performance with my proposed method?

What about doing cross validation on your training set? Once you have the different train/test splits I would start by printing the accuracy (number of correct predictions / total predictions) and the ...
h3h325's user avatar
  • 253
3 votes

Is splitting the data set into train and validation applicable in unsupervised learning?

For an unsupervised technique, if you have some metric of "goodness of fit", it makes sense to have a train-test split. In your case, it seems as though you'd want to split the data so that you can ...
David Atlas's user avatar
3 votes

Setting best SVM hyper parameters

Well, there is a bunch of articles that tries to tackle this problem but basically, to guarantee a good solution you will need to do Grid Search (sklearn tutorial on it) You can use various ...
Pedro Henrique Monforte's user avatar
3 votes
Accepted

How to find which features have been selected by PCA algorithm?

PCA doesn't remove any specific feature. What PCA does it to calculate linear combinations of your variables in such way that they get "summarized" in fewer variables. You don't eliminate variables, ...
Juan Esteban de la Calle's user avatar
2 votes
Accepted

Using the trainbr function for classification in Matlab

The trainbr mode uses the Bayesian regularization backpropagation. This method was presented in 1, which presents a regression problem with the loss function $$ E_D ...
hbaderts's user avatar
  • 1,114
2 votes

What type of optimization problem is this?

Some flavor of evolutionary algorithm may suit your problem nicely, since: The gradient of the objective function is unavailable or cannot be computed. The objective function itself is somewhat ...
scherm's user avatar
  • 171
2 votes
Accepted

Issue with backpropagation using a 2 layer network and softmax

I think it might be a relatively trivial bug in your cost function for softmax: J = -(sum(sum((Y).*log(h))) + lambda*p/(2*m)) should be ...
Neil Slater's user avatar
2 votes
Accepted

Implementing PatterNet in Python as it is in MATLAB

Consider reusing an existing framework and adding the missing activation functions. For example, here you can see how to do that in sklearn. However, notice that ...
mapto's user avatar
  • 744
2 votes

Why training and validation similar loss curves lead to poor performance

to prevent overfitting in a model the training curve in a loss graph should be similar to the validation curve. That's not always the case, maybe the train set has slightly a different ...
Fadi Bakoura's user avatar
2 votes

Why training and validation similar loss curves lead to poor performance

to prevent overfitting in a model the training curve in a loss graph should be similar to the validation curve Similar in what way? If your training error keeps decreasing and the validation error ...
Alex's user avatar
  • 767
2 votes

How to make sense of confusion matrix

1) It depends in what you define as positive and negative. Generally, and in particular in medicine, people tend to label $0$ as negatives and $1$ as positives, thus being $1$ the abnormal case. But ...
David Masip's user avatar
  • 6,101
2 votes

Is ensemble learning using different classifier combination another name for Boosting?

Ensemble learning combines predictions from multiple learners. Boosting methods are one way to form an ensemble. Stacking is another. The important difference between boosting and stacking (and other ...
oW_'s user avatar
  • 6,377
2 votes
Accepted

Is ensemble learning using different classifier combination another name for Boosting?

Boosting is a type of Ensemble Learning, but it is not the only one. Apart from stacking, bagging is also another type of Ensemble Learning. Ensemble Learning is the combination of individual models ...
Christos Karatsalos's user avatar
2 votes
Accepted

Poor performance of SVM after training for rare events

This I can say because I ran the trained model on the entire dataset again (re-trained it) an predicted on the same dataset. You seem to be making a fundamental mistake here. If you train and test ...
Valentin Calomme's user avatar
2 votes

Graphically Speaking - how weight vector is perpendicular to hyperplane

I think if you play with the scales of the axes and the viewing angle, you may find it is perpendicular. Especially, try to rotate the view that you look sideways to the plane. You will see the ...
Pieter21's user avatar
  • 1,041
2 votes
Accepted

Accuracy differs between MATLAB and scikit-learn for a decision tree

It is hard to make a direct comparison between a white box implementation (scikit-learn) and a black box implementation (MATLAB). One guess they are using different algorithms. scikit-learn uses an ...
Brian Spiering's user avatar
2 votes

Convolution Neural Networks on microcontrollers

What you are looking for is often called an inference engine. Tensorflow Lite for microcontrollers was just announced. I have not seen anyone use it on PIC32, but it should be possible to port it to ...
Jon Nordby's user avatar
  • 1,527
2 votes

Convolution Neural Networks on microcontrollers

Implementing any of this from scratch is not for the faint of heart... Well, I am not familiar with PIC32, but you can see a CNN as... How to implement: Where I*CKN detones the convolution of the ...
Pedro Henrique Monforte's user avatar

Only top scored, non community-wiki answers of a minimum length are eligible