Stack Exchange Network

Stack Exchange network consists of 174 Q&A communities including Stack Overflow, the largest, most trusted online community for developers to learn, share their knowledge, and build their careers.

Visit Stack Exchange

Questions tagged [machine-learning]

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

0
votes
1answer
24 views

python: why add new features of image to be worse result with xgboost

there are about 93 rows of data with features, two classes label. And, there are about 49 one-hot value features, and there are about 10 features continuous value. I split the data randomly by train ...
1
vote
0answers
9 views

Unusual Memory trends while using Densenet

I am using Densenet to train my model but I found some unusual trends of memory usage while training the network, it follows the normal curve. I am unable to understand this can somebody help me ...
0
votes
0answers
8 views

Image Segmentation-Tumour Identificaiton

I have a data set consists of 3d images with format(.nii). How do i convert those images to 2d to perform segmentation.med2img is showing syntax error for me.
0
votes
1answer
26 views

How to properly rotate image and labels for semantic segmentation data augmentation in Tensorflow?

What's a proper procedure for doing the image and label rotation for semantic segmentation in dataset augmentation using Tensorflow? Images I have seen the function tf.contib.image.rotate(), but ...
2
votes
1answer
33 views

How does Gradient Descent and Backpropagation work together?

Please forgive me as I am new to this. I have attached a diagram trying to model my understanding of neural network and Back-propagation? From videos on coursera and resources online I formed the ...
0
votes
0answers
20 views

Calculating sin function with neural network using python

I'm new in deep learning and trying to create a basic neural network for sin function. I have generated numpy array with random values of shape (50,1) which outputs sin(input). The neural network ...
1
vote
0answers
44 views

Word classification (not text classification) using NLP [closed]

I have been trying to extract Person name and Company name out of string. But, I have been facing lot of difficulties. I have a dataset of names and a dataset of company names. In the string, I wish ...
0
votes
1answer
21 views

Predict upcoming coordinates

Given sequences of points that define similar lines amongst each others, e.g: Where the blue lines are similar to each other, given the red point sequence and assuming that it will follow the same ...
0
votes
0answers
24 views

How to check whether word is abbreviated or not using python [migrated]

How to check whether word is abbreviated or not in dataframe column using python. For instance, U.S.A value I need to detect it as abbreviation. Is there any dictionary present for this?
1
vote
2answers
43 views

How to investigate what has been learnt in CNNs?

My CNN was trained using close-up images of dogs. For testing, we input an image with a dog next to its owner and it was classified as a dog. How is that possible? ...
0
votes
0answers
14 views

Machine Learning algorithm to get X and Y points ranges values

I have a dataset that looks like this: ...
0
votes
1answer
15 views

Model accuracy changes when target attribute change [closed]

I have a dataset. For a target attribute for example:person, I get an accuracy which is different when I use for example:price as target attribute and so on. Why this accuracy keep changing?
0
votes
0answers
15 views

Unbalanced data set

Good evening everyone, I'd like to train a dataset for a multiclass classification. The problem is my dataset is very unbalanced. I mean, i have lots of elements from a class and few from another. I'...
1
vote
1answer
31 views

Keras inconsistent training results

I have a CNN network in keras. I do the training on a cloud GPU. I get completely different accuracy and loss graphs when I run the training twice. I set random seeds as below, still no luck. Anything ...
0
votes
1answer
19 views

Machine learning algorithm to classify matrices [closed]

I want to know what could be first choice for a machine learning algorithm to classify matrices. Each matrix belongs to either class A or class B. The classification problem is: To classify each ...
0
votes
0answers
14 views

Does sum of embeddings make sense?

Referring to the LightFM model from paper Metadata Embeddings for User and Item Cold-start Recommendations, the model tries to learn $d$-dimensional user and item feature embeddings $e_f^U$ and $e_f^...
0
votes
0answers
8 views

What are the best encoding methods for Insurance Claims?

I have some categorical with quantitative data in a Dataset of insurance claims that I need to encode in order to apply PCA and later Isolation Forest in order to detect outliers in the Auto Insurance ...
0
votes
0answers
11 views

Training InceptionV3/Resnet on custom data with CoreML/CreateML

I'm new to the CoreML/CreateML scene. I know that there is an image classifier built by Apple that can be easily trained by drag/dropping data, with pretty good accuracy. What I am wondering is, is ...
1
vote
1answer
33 views

Multi-label classification for text messages (convert text to numeric vector)

Given a dataset of messages which are labeled with 20 features, I want to predict the value of each feature for a new message. Dataset example: ...
0
votes
0answers
15 views

What kind of math do I need to use when I want to apply machine/deep learning for embedded systems?

This is my first post here in this section. I have built a C-library for computing matrices and I going to use that for system identification, which IMO i think is a part of machine learning, even if ...
2
votes
1answer
50 views

Stop CNN model at high accuracy and low loss rate?

I train my CNN model with a large number of epochs, with each epoch I print the training loss and accuracy, but there is a lot of high and low in these two metrics, I want to do early stopping with ...
0
votes
0answers
18 views

Multivariate time series forecasting without historical data

I have a dataset similar to the example below: It contains some categorical data (e.g. business type, business size, location) and the time-series of energy consumption from Time 1 to Time N with a ...
0
votes
2answers
24 views

How to handle non consistent time series( using LSTM )

The time series dataset I am working on has missing samples. I am trying to use keras and LSTM for prediction. How should I handle the missing timestamp samples ( sometimes there are missing weeks ...
1
vote
1answer
30 views

Why Huber loss has its form?

Huber loss formula is $\hspace{3.0cm} L_\delta(a) = \begin{cases} \frac{1}{2} a^2 && |a| \leq \delta \\ \delta (|a| - \frac{1}{2} \delta) && |a| > \delta\end{cases}$ where $a = y - ...
0
votes
0answers
13 views

ctc forward backward algorithm - why is it being used?

as per ftp://ftp.idsia.ch/pub/juergen/icml2006.pdf fwd bw algo helps us speed up discovery of the happy path. For e.g. if the GT label is DOG and we have 10 time steps , the possible label sequences ...
0
votes
0answers
26 views

ML algorithms for regression in the case of label noise with a known distribution?

I'm pretty new to machine learning, and I am interested in some ideas for algorithms or references for papers for using a ML algorithm for regression when the labeled data has label noise with a known ...
0
votes
1answer
47 views

Adding dense layer to CNN causes to stop learning

I have 6 layer CNN model that (kind of) works with "GlobalAveragePooling2D()" in the end but instead if I flatten and add dense layers like below, it just does not learn. After 20 epochs loss and ...
2
votes
1answer
51 views

Finding a Data pattern [closed]

I am new to this data science field. I have data of points in 3D space and each point "helps" a metric. I have the sets of points and corresponding metrics. Data might look like: ...
0
votes
1answer
16 views

What is advantage of using the theory of point processes instead of probability distribution functions?

I am interested in applications of point processes in machine learning, so I have been studying the theory of point process. However, I cannot see advantage of the theory of point processes compared ...
0
votes
0answers
24 views

Basic code flow for training and finalizing models using sk_learn

I am new to machine learning. I am trying to implement a regression solution in my product, using sk-learn library. I came up with below execution plan. Please help me by reviewing the same. [1] ...
0
votes
0answers
13 views

How to balance specificity and sensitivity?

I have included accuracy and feature minimization in my fitness function. How should I balance specificity and sensitivity?
0
votes
0answers
11 views

Verify compliance with the laws in text documents

USE CASE - AS IS A user sends a text document X to a system where it requires a s service (for example, to request a residence permit). A technician examines the document verifying that the document ...
1
vote
1answer
28 views

Similar students using Machine Learning

I have a student performance data, where I have marks of various subjects for the students and I want to find similar students with good marks in a particular subject using machine learning. How do I ...
0
votes
1answer
27 views

Am I justified in dropping this independent variable?

I'm currently doing churn prediction in R and during EDA, I discovered that a variable, say gender, has 1720 males who don't churn, and 280 males who do. Also, it has 864 females who don't churn, and ...
0
votes
0answers
17 views

About applying time series forecasting to problems better suited for reinforcement learning, like toy example “Jack's car rental”

"Jack's car rental" is an example of a reinforcement learning problem, proposed in the Sutton & Barto book, in which the goal is to optimize the daily distribution of cars in two locations of the ...
0
votes
1answer
14 views

Why is “next state” kept in RL experience replay?

Following this explanation on what is experience replay (and others), I noticed an experience element is defined as $e_t = (s_t,a_t,r_t,s_{t+1})$ My question is, why do we need the ...
1
vote
2answers
31 views

Training Examples used in Stochastic Gradient Descent

Hi I was reading the difference between GD and SGD and found the below link. [What is the difference between Gradient Descent and Stochastic Gradient Descent? Based on this information I wanted to ...
0
votes
2answers
34 views

Decentralized machine learning

Currently, to train a model, you need to collect a huge blob of data. Are there feasible concepts of decentralized machine learning? Like, feed the model somehow from isolated data sources, or merge ...
0
votes
0answers
16 views

What is the best statistical measure tool or approach to resolve my problem?

I have a dataframe from different sources with this index and 1 column. My goal is to detect which source_i have a different counter behavior per time. The first thing I did simple prediction using ...
0
votes
1answer
39 views

Using Image Data along with CSV file data for CNN model

I have image data along with csv file where each row of csv file contains attributes for corresponding image. I want to use images as well as csv file data to build CNN model using Keras. What is ...
0
votes
1answer
22 views

How can we apply PCA to reduce dimensionality of a heterogenous dataset?

I have a dataset containing insurance Claims with quantitative and qualitative variables but PCA refuses to convert or work with "string" type variables. This is the code I used : ...
0
votes
0answers
11 views

Why do we reduce magnitude of the coefficient in regression

Why do we reduce the magnitude of the coefficient in regression? how does it help the model?
1
vote
0answers
13 views

I have payments data and I need suggestions from experts what can I do

I have data for a local payment service that is not compatible with standards for electronic payment services such as Visa cards. The service depends on sending a message to the buyer from the ...
0
votes
0answers
19 views

Is setting class weight to 0 in Keras fit_generator equivalent to ignoring the class during training?

According to the Keras documentation, class_weight is a dictionary mapping class indices (integers) to a weight (float) value, used for weighting the loss function. So does that mean giving a class a ...
0
votes
1answer
25 views

Comparative Analysis of two sets of data

I have 2 sets of data which consist of marks of 60 students in a particular subject in year 1 and year 2 respectively. Year 1 : 86, 76, 87, 67, 89, 95.... so on (60 students) Year 2 : 82, 67, 99, 77,...
0
votes
1answer
18 views

Confusion on Delta Rule and Error

I'm currently reading Mitchell's book for Machine Learning, and he just started gradient descent. There's one part that's really confusing me. At one point, he gives this equation for the error of a ...
2
votes
2answers
75 views

Sports prediction using machine learning [closed]

I am trying to predict soccer scores using past results. The dataset I have only consists of the home team, the away team, goals scored by the home team and goals scored by the away team in each match....
1
vote
4answers
79 views

What Unsupervised Machine Learning algorithms can be used to detect Fraud in insurance?

I'm about to start a project regarding Fraud Detection in Insurance but there is no dependant variable to train the model and classify it. Please provide the algorithms that I can use to detect Fraud ...
1
vote
2answers
37 views

Reg. Pandas factorize()

-Hi Experts- I just read about factorise() function in Pandas. Using this I'm able to encode (enumerate) my string values into numbers. But, now I'm not able to understand what numbers corresponds ...
0
votes
2answers
39 views

Classification: how to handle reviews/long english words in feature set with all other numerical features

I am currently working on an use case where feature set contains numeric values such as amount, as well as a review feature which contains long winded english text. the english text will very well ...