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
7 views

What exactly is .csv in machine learning?

I already have dataset of dogs and cats , so do i need to make .csv file or can i directly use the dataset for classification
14
votes
6answers
2k views

Data science related funny quotes and jokes

It has been customary for the users of different communities to quote funny things about there fields. It is almost Christmas and after a long journey, it may be fun to share your funny things about ...
0
votes
1answer
9 views

What are some good design practices for creating/improving a CNN?

Recently I've been working on a mini side project in detecting age off of facial images. Aside from mistakes, I have made decent progress in creating my model. ...
1
vote
1answer
50 views

boosting an xgboost classifier with another xgboost classifier using different sets of features

What I would like to do, is train a first model $f_{1}(\underline{x})$, where $\underline{x}$ is a set of features, fix what model 1 has learned, and then train a second model $f_{2}(\underline{y})$ ...
0
votes
1answer
13 views

GD for logistic regression isn't stable. Why?

Here's my (incomplete) implementation for linear regression using GD: ...
0
votes
1answer
57 views

Derivation of dz[1] for backpropagation

Can anyone mathematically prove this equation given the values of $dz^{[2]}$, $W^{[2]}$, $z^{[1]}$ and the activation function $g^{[1]}$ $dz^{[1]} = w^{[2]T}dz^{[2]} * g^{[1]'}(z^{[1]})$
1
vote
0answers
3 views

formalizing the machine learning model training by incorporating the human involvement

In some learning system designs, sometimes we incorporate a user-interface that enable the users or domain experts to manually change the models by some operations such as, change the rules or some ...
2
votes
2answers
27 views

What is the relation between input into LSTM and number of cells?

I want to train an LSTM network for time-series predictions, and want to get to the bottom of LSTM's. In my understanding, the number of cells in a single LSTM layer can vary. However, since each cell ...
1
vote
1answer
40 views

CNN - Is this a Toeplitz Matrix?

I have been reading through Chapter 9 of www.deeplearningbbook.org, where convolutional networks are being described. The following image represents the output of a 2D convolution, without kernel ...
1
vote
1answer
20 views

How to find similarity of two series over time containing periodic trends?

Considering the data is received from a streaming source each second.How to distinguish if both the line graphs 'look' same/different in real time, statically, like the picture given below Edit: 1....
0
votes
0answers
8 views

how to give input for text classification for cnn?

I have a 8897×50 matrix. In this matrix,each row represents a sentence and in every sentence there are 50 words.Everything is in vectorized form.But,this input is not taken by cnn.How can I solve this ...
0
votes
1answer
59 views

Is my model over-fitting (LSTM,GRU)

I have small corpus max 150 text utterances, which is again distributed among 5 categories. To test I started with basic deep learning model, where i used word2vec embedding, added 1D convolution ...
1
vote
0answers
22 views

What does Machine Learning Paradigms means, and what are they? [on hold]

Please, help me to properly answer the following (main) question: What does machine learning paradigms means? And, what are they? I tried to answer this questions myself, but two completely ...
1
vote
1answer
21 views

Calibrate the predicted class probability to make it represent a true probability?

Let's say that we have a simple binary classification model (a neural network -- NN) for classifying input images as "dog" ($y=1$) or "not dog" ($y=0$). Let's assume that the NN has one "sigmoid ...
0
votes
0answers
7 views

How to get features representing a data point if its distance is known from center of a cluster

I got distances of 10 nearest data points in a cluster (ith cluster) from its center by doing:- ...
0
votes
2answers
22 views

Cash-flow prediction with machine learning

In our company we have huge incoming cash flows every day. Having a very good prediction on the incoming cash flows for the next working day would be for various reasons very useful. As for the data:...
1
vote
2answers
23 views

What are the possible approaches to fixing Overfitting on a CNN?

Currently I am trying to make a cnn that would allow for age detection on facial images. My dataset has the following shape where the images are grayscale. ...
0
votes
1answer
35 views

Using GridSearchCV and a Random Forest Regressor with the same parameters gives different results

As the huge title says I'm trying to use GridSearchCV to find the best parameters for a Random Forest Regressor and I'm measuring my results with mse. ...
0
votes
0answers
2 views

What is the best proprocessing steps for DICOM CT images

I am working on DICOM lung CT images, there are some preprocessing to do on images such as Converting the pixel values to Hounsfield Units (HU), Resampling, segmentation, Normalization, and Zero ...
2
votes
1answer
64 views

Is color information only extracted in the first input layer of a convolutional neural network?

In a convolutional neural network (CNN), since the RGB values get multiplied in the first convolutional layer, does this mean that color is essentially only extracted in the very first layer? ...
0
votes
0answers
16 views

Which model for Kaggle Diabetic Retinopathy Image Dataset?

What model is the best to use on this Kaggle dataset, such that there is about a >70% accuracy but is not too resource intensive for say a desktop? Is this even possible? Should I go for a deep ...
1
vote
1answer
25 views

Do I use actual data or data difference to train machine learning model?

I would like to predict tomorrows temperature :-). But I'm unsure of the best approach. Do I simply drop data from the last x days, or do I try do drop data from the last x days in difference? Last ...
0
votes
0answers
7 views

Determing which GIVEN topic a question belongs to?

I have 1000 questions and each of them has to be assigned to a topic out of 'n' number of already given topics. example: Question -- Can a unique key take many NULL values? Topics -- Keys, Object,...
0
votes
1answer
42 views

Process mining with ML

I have a little more general question. My dataset consists of N sequences of events. Example of one sequence could be [A,B,C,D,X,Y] and another [A,B,Z], where letters represent different events. The ...
0
votes
1answer
137 views

Should the cost function be zero using TensorFlow's sigmoid_cross_entropy_with_logits?

I'm building a CNN to make a binary classification (1 or zero). For this I'm using the cost function sigmoid_cross_entropy_with_logits. But for some reason the ...
1
vote
2answers
82 views

Logistic Regression Cost Function: Gives mathematical error since its attempting to calculate log(0)

I am learning machine learning and after reading through materials on logistic regression i attempted to implement logistic regression with gradient descent in python from scratch. It works well for ...
1
vote
3answers
21 views

Should I build a different model for each subset

I have a dataset which has categorical variable class. I am trying to solve a regression problem I am not understanding whether I should build a model on entire dataset and consider variable class as ...
0
votes
1answer
28 views

Predicting next number in a sequence - data analysis

I am a machine learning newbie and I am working on a project where I'm given a sequence of integers all of which are in the range 0 to 70. My goal is to predict the next integer in the sequence given ...
0
votes
0answers
7 views

Thresholded shortest path distance

In impressing DeepMind's paper Human-level performance in first-person multiplayer games with population-based deep reinforcement learning, there is an attempt to classify and extract agents' ...
1
vote
0answers
12 views

Is there a good online course for working with sklearn MLPClassifier?

I'am implementing an App for which I need a neural network. Because: I want to classify each DOM-text-element of an webpage which conains any curriculum vitae of a person. The neural network should be ...
0
votes
1answer
11 views

I have data with customer personal information and customer transaction. I cannot figure out how to use the data for training my model?

Customer information attributes: ID Age Gender State etc Customer transaction ID Store ID No of items bought State etc Store info Store ID State Daily revenue Store size etc I want to predict if ...
1
vote
1answer
170 views

How to create a dummy model in Tensorflow

I am a newbie in Machine learning. I found this example using tflearn somewhere. It is the part of the program where we initialize a dummy model before training ...
2
votes
1answer
62 views

Backpropagation

I use chain rule when doing backpropagation and then I do Gradient Descent with weighting coefficient and I am updating the weight, so I do not understand how the method works in the equations below. ...
3
votes
1answer
67 views

Extract features from a survey

I need to use the answers from a questionnaire for training a classifier. I discovered that some questions can have nested sub-questions.. Let's say (just an example) that I want to predict whether a ...
1
vote
1answer
39 views

Is a neural network able to learn to map a completely different feature vector to the same class

Is a neural network (for example a MLPClassifier in Python) able to learn to map a completely (or very) different input feature set to the same output class? Or is it better to work in this case with ...
0
votes
3answers
31 views

Meaning of variance in machine learning models

I know that high variance cause overfitting, and high variance is that the model is sensitive to outliers. But can I say Variance is that when the predicted points are too prolonged lead to high ...
0
votes
0answers
10 views

could not convert string to float: 'W./C. 6607' [on hold]

from sklearn.preprocessing import OneHotEncoder labels=OneHotEncoder() labels.fit_transform(x).toarray Error: ...
1
vote
1answer
164 views

Confusion about Keras' skipgram and sampling table utilities

I'm fairly new to ML, so as a learning exercise to get familiar with Keras I'm trying to learn some word2vec style embeddings from a dataset. I'm confused about the behavior of the skipgram utility, ...
0
votes
0answers
3 views

Hyper-parameter tuning when you don't have an access to the test data

I'm building models for SQUAD (Stanford Question Answering) dataset (https://rajpurkar.github.io/SQuAD-explorer). Stanford doesn't release its test set. It only provides us with training and dev ...
3
votes
1answer
51 views

Classifying Car Data By Year

I have huge car photos. I want to predict car's "brand-model-body type and production year" First, I splitted data into train and validation, and I categorized them like this. Every category has ...
1
vote
2answers
18 views

How would I be able to improve my CNN model (Keras)?

Recently I read a research paper on age detection using facial images. So right now because of that I was trying to see how far I could get by applying a CNN to a dataset of facial images (with their ...
1
vote
1answer
27 views

Why does a filter need to be applied to the output of the input gate before cell state is added to?

In a neural network there are 4 gates: input, output, forget and a gate whose output performs element wise multiplication with the output of the input gate, which is added to the cell state (I don't ...
1
vote
1answer
7 views

Should estimated probabilities from multi class classification sum to 1

I am using a neural network with sigmoid activation function $h(z) = 1 / {(1+e^{-z})} $ in order to classify image data into 6 categories. When running the trained neural network over new image data, ...
1
vote
1answer
17 views

Deep learning: Training in batches [duplicate]

How does training in batches help in obtaining a better deep learning model? What should one keep in mind while splitting data into batches?
1
vote
1answer
26 views

Can a neural network recognize a letter B as an A if your trained it so?

You have a neural network. And you have, say, pictures of $100,000$ hand-written letters (A-Z). Now you make a typical Training and the neural network will recognize an A as an A, a B as a B, ... Now ...
56
votes
5answers
29k views

Why do cost functions use the square error?

I'm just getting started with some machine learning, and until now I have been dealing with linear regression over one variable. I have learnt that there is a hypothesis, which is: $h_\theta(x)=\...
2
votes
1answer
72 views

Dynamic clustering

I am performing anomaly detection on different datasets and thought to first cluster the dataset and submit each of the clusters to different AD models. I am using HDBSCAN, and in my test dataset I ...
3
votes
1answer
26 views

Do CNNs benefit from HDR images?

I have images with 12 bits per color channel which I use for several detection networks (YOLO, RetinaNet, etc.). Can I expect any precision difference between 12 bpp and 8 bpp as network input? Or is ...
2
votes
2answers
6k views

What does RMSE points about performance of a model in machine learning?

I am working on Decision Tree algorithm and at the end I calculate RMSE value based on actual labels and predicted values (for ...
0
votes
1answer
36 views

How to set the parameters of a Hidden Markov Model that'll be used to correct the mistakes by a previous classifier?

Say we've previously used a neural network or some other classifier C with $N$ training samples $I:=\{I_1,...I_N\}$ (that has a sequence or context, but is ignored by C) the, belonging to $K$ classes. ...