Methods and principles of building "computer systems that automatically improve with experience."

learn more… | top users | synonyms (1)

1
vote
1answer
20 views

Quadratic error for multi-class classification

I'm trying to train a neural network to classify handwritten inputs into 10 categories, each for one digit (1,...,9,0). I represent the output of an example using a 10-dimensional vector. Digit 5, for ...
0
votes
0answers
35 views

Problem with backpropagation algorithm for Feedforward Neural Networks

The objective When trying to exercise my knowledge of Feedforward Neural Networks, I started implementing one. The result is here. The final goal is to predict some handwritten digits data I have. ...
3
votes
1answer
52 views

Understanding the use of logarithms in the TF-IDF logarithm

I was reading: https://en.wikipedia.org/wiki/Tf%E2%80%93idf#Definition But I cannot seem to understand exactly why the formula was constructed teh way it is. What I do Understand: iDF should at ...
1
vote
1answer
29 views

Need guidance in image classification

I'm new to machine learning and need some help. I need image classification to tell if an image is a car or not. Is there any working example or guidance or a book for this particular question? ...
0
votes
2answers
39 views

Multi-label classification

I am working on a project and I need some suggestions. I have a data set with 600 songs and for each song we have 60 numerical features (linked to the rhythm and the timbre of the sound). Moreover ...
1
vote
0answers
26 views

What is a compact vector equation expression the back-propagation algorithm for convolution neural networks?

I was reading the lecture notes for sparse auto-encoders from Andrew Ng and was saw that it had very nice compact way of expressing back propagation for neural networks: The really nice thing about ...
0
votes
0answers
35 views

Application of probability-inequalities in machine learning. Hoeffding's inequality

I would like to know a illustrative example of Hoeffding's inequality in machine learning? Does it have something to do with confidence intervals? Thanks in advance!
0
votes
0answers
6 views

Which regression model to use for order-sensitive sequences of symbols / apps?

I have a list of sequences of symbols, representing apps used by a smartphone user within a certain time frame. For example (Whatsapp, Facebook, Calender) might be one such sequence. To each list ...
2
votes
1answer
56 views

Predicting the winner of a contest, given history

In one of the online games I play, there's a daily contest where users can make bets. I'm hoping I can place more profitable bets by analyzing the contest's history :) (Though really I just wanna ...
1
vote
0answers
12 views

Training A Restricted Boltzmann Machine with gray-scale images

I am trying to train a feed forward neural net for image classification. In this process, I am implementing a restricted boltzmann machine to help pre-train the weights. My images are grey-scale ...
0
votes
0answers
18 views

How to approach clustering when each object does not have the same number of qualities

I would like to apply a clustering algorithm to a set where each observation does not have the same number of "qualities". I have searched extensively online for this problem and were unable to find a ...
0
votes
1answer
28 views

Machine Learning: Stratified Test-train-validation split for images with multiple classes and examples per image

I have a dataset with 300 images, each of which has a variable number of flowers. These flower examples can be any of 3 classes. My goal is to develop a prediction algorithm to classify the flower ...
0
votes
2answers
33 views

Minimization parameters on machine learning

Hello I'm studying machine learning processes and I'm beside of a misunderstanding.. Is this right? "Minimization is a process that minimize the error rate of Y (output of the feature) to be a ...
2
votes
1answer
49 views

Supervised dimensionality reduction

I have a data set consisting of 15K labeled samples (of 10 groups). I want to apply dimensionality reduction into 2 dimensions, that would take into consideration the knowledge of the labels. When I ...
1
vote
0answers
29 views

Which classification techniques perform efficiently under homomorphic encryption

I am reading a paper (pdf) on homomorphic encryption and its use in machine learning. This paper explores classification methods like Fisher Linear Discriminant Classifier (FLD) and the Linear Means ...
0
votes
0answers
20 views

Equivalent measure to Matthews correlation coefficient, MCC, for multiclass classification

Thanks in advance for the help. MCC gives a measure of the quality of a binary classifier. I'm looking for a similar measure that can be used for a multi-class classifier. Ultimately what I would ...
0
votes
1answer
35 views

Latent Dirichlet Allocation - definitions

I am self-studying the article on LDA by Blei, Ng and Jordan (https://www.cs.princeton.edu/~blei/papers/BleiNgJordan2003.pdf). at the start of the second section - the following definitions are given: ...
1
vote
0answers
33 views

Regression Tree Predictions

For various regression tree algorithms (e.g. GBM, Random Forest, Extra Trees), is there any sensible way to get predictions for new data when the independent variables for the new cases are much ...
1
vote
0answers
29 views

Meaning of $\sum_{i=1}^n \alpha_i<n-t$ in svm? and it's primal countepart

Consider svm-dual,i.e., \begin{align} &\text{maximize} \sum_{i=1}^n \alpha_i-\frac{1}{2\lambda} \sum_{i,j=1}^n \alpha_i \alpha_j y_i y_j K(x_i,x_j)\cr &\text{subject to, } 0\leq \alpha_i ...
0
votes
1answer
70 views

Train a Neural Network to distinguish between even and odd numbers

Question: is it possible to train a NN to distinguish between odd and even numbers only using as input the numbers themselves? I have the following dataset: ...
1
vote
1answer
20 views

How does linear SVMs function in multi dimensional feature space

Can someone please explain me how does linear SVMs function in multi dimensional feature space ? I'm not able to picture how a linear SVM can perform classification in more than 2 dimensions. Also, ...
0
votes
0answers
41 views

Obfuscating sensitive data keeping data-properties intact

I am preparing a dataset for my academic interests. The original dataset contains sensitive information from transactions, like Credit card no, ...
1
vote
1answer
29 views

Friend or Foe Q Learning Algorithm Q-Value Update

I'm trying to learn how to update the Q-values for FFQ (paper available here), but I'm stumbling over the notation and can't seem to figure out exactly what it wants me to do. From the paper: ...
0
votes
3answers
112 views

What is the difference between logistic regression and bayesian logistic regression?

I'm a bit confused whether these two are the same concept. If they are different what's the difference? Thanks!
0
votes
1answer
42 views

What does the equation $h^k = \sigma(x * W^K + b^k)$ mean in the context of convolutional neural networks (CNNs)?

I was reading a paper on CNN for auto-encoders and in section 3 they had the following section: For a mono-channel input $x$ the latent representation of the k-th feature map is given by $$ h^k ...
2
votes
2answers
80 views

How exactly do convolutional neural networks use convolution in place of matrix multiplication?

I was reading Yoshua Bengio's Book on deep learning and it says on page 224: Convolutional networks are simply neural networks that use convolution in place of general matrix multiplication in at ...
0
votes
0answers
35 views

Forecasting time series with lagged variables and machine learning

I want to forecast a time series based on the lagged variables of the model and train it using a machine learning algorithm like Random Forest, SVM, Neronal Network, etc. So I want to forecast A ...
0
votes
0answers
16 views

Fine Tune Model with Caret Package

I am using CARET package to fine tune random forest mtry parameter. In the package, tunelength parameter can be used to automate search for best mtry parameter. But the problem is the "tunelength" ...
1
vote
0answers
34 views

Why do auto-encoders with 1 hidden layer usually use the output weights/filter as $W=W^T$?

I was trying to understand why for auto-encoders with 1 hidden layer, we usually use the output weights/filter as $W=W^T$. Is there any theoretical justification to use $W=W^T$? Or maybe any way to ...
1
vote
0answers
21 views

How can I extract features from fMRI network connectivity analysis (FSL nets)?

I have a set of 37 fMRI images from mice which are divided into 4 classes (different drug doses applied). My task is to train classifiers (SVM etc.) on this dataset. Of course feature extraction is a ...
0
votes
0answers
226 views

Gaussian Processes for Stock Market

I'm reading this paper and I would like to implement it. It gives me a matrix in this way: $$ \begin{array}{lcr} \mbox{Year} & \mbox{day 1} & \mbox{day 2} & \dots & \mbox{day 250} ...
1
vote
0answers
30 views

Reinforcement Learning for Multiple Agents

I already have a functioning $Q(\lambda)$ implementation for a single agent working on a dynamic pricing problem with the goal of maximizing revenue. The problem that I'm working with, however, ...
1
vote
0answers
11 views

Detecting 'unusual behavior' using machine learning with Redis and Python?

I am developing client application using python . It will listening the redis queue (subpub) and doing some suppression and aggregations . Eg msg from redis :- CPU 80% full critical CPU 80% full ...
3
votes
1answer
55 views

Understand the reason for calculating the MSE

Im following an introduction course into R-machine Learning. Im doing the following: Load the faithful dataset (standard in R) Creating a model that predicts waiting time -> eruptions of the first ...
0
votes
0answers
7 views

Softmax Regression Large Inner Product Float Overflow

In softmax regression, the probability $P$ that an item is part of class $l$ is given by $$P(y^{(i)}=l | x^{(i)};\theta)=\frac{e^{\theta^Tx^{(i)}}}{\sum_{j=1}^k e^{\theta^Tx^{(j)}}}$$ I have ...
0
votes
0answers
13 views

Finding keywords in small pieces of text.

I'm (attempting to) construct a bayesian neural network to parse through tweets to then decide if someone bought/sold something and for how much. I'm having trouble figuring out what the input nodes ...
0
votes
0answers
13 views

Multi-label multinomial logistic regression

I have stock data with about 50000 features and 20 labels. Each of the label can take one of three values: -1, 0, 1. I've divided the data in 9:1 ratio so that nine tenth of the data is used to ...
0
votes
1answer
29 views

Number of nodes in hidden layers of neural network

I have a neural network with 3 hidden layers and I'm unsure about the number of hidden nodes for each layer. Should the number of hidden nodes stay constant between the hidden layers, e.g. 500 nodes ...
0
votes
2answers
78 views

Linear regression to determine risk of failing system

I have a running process that pings multiple servers to check they are alive. If a server is taking a long period of time to respond (>10 seconds) then this system is actioned. I plan to automate the ...
2
votes
1answer
48 views

Why is random forest inconsistent in text mining?

Earlier I've used SVM (rbf kernel) in text mining with success, and after that for similar text mining work with long texts I've used random forest with success as well. However in a recent kaggle ...
0
votes
0answers
19 views

How to deal with, and use, missing data (MNAR) in svm?

I am trying to predict future spending of customers based on past transactions. My data looks as follows: ...
1
vote
0answers
6 views

Inference from the posterior predictive distribution [duplicate]

I want to use Bayesian model to predict the values of signal in the future. The process is like: a. 1000 observations are given. First 800 consecutive observations are training data, and 200 ...
0
votes
0answers
21 views

How to use Naive Bayes classifier to predict three different outcomes?

My training data consists of the last season results in the following format (.csv file): ...
1
vote
1answer
17 views

Is it possible for test error to be lower than training error

Is it possible to have test error lower than training error? I have a classification problem with 2000 samples, 500 of which are positives, 1500 are negatives. I split my data into 70% training data, ...
1
vote
1answer
38 views

Use of a bagging model or feature engineering?

As a pet project, I have been learning some data analysis and machine learning skills (mainly text analytics) with the Analytics Edge course on edX. I decided to put some of my new skills at use ...
0
votes
0answers
9 views

Representative signal

I'm implementing machine learning with sensor data. I am having the problem that some sensors not always have good integrity, that is, not all data points arrive at destination because of ...
0
votes
1answer
17 views

Notation - stacked vectors

I am trying to self-study Kevin Murphy's book on machine learning. i am trying to be 100% sure that i understand the notation in the book. . I am however struggling to understand what is meant with ...
0
votes
0answers
34 views

How does the convolution work for a simple example 1D and its relation to the true mathematical convolution?

I was trying to pin point precisely mathematically what the convolution does for a simple 1D example (i.e. $x \in \mathbb{R}^D$ as opposed to an image $x \in \mathbb{R}^{D_1 \times D_2}$). The ...
1
vote
1answer
46 views

A question about Dynamic Random Forest

On this article, Simon Bernard proposes a new approach for constructing Random Forest called Dynamic Random Forest. I am new on this subject, so after reading the article, I have a doubt regarding the ...
0
votes
0answers
19 views

Integrate a function over variable following normal distribution in R [migrated]

I want to integrate the inverse logit function over a variable $X$, which follows a normal distribution, $X\sim N(21,7)$. I'm a beginner in R so i have been trying following commands that didn't work ...