Questions tagged [machine-learning]

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

Filter by
Sorted by
Tagged with
0
votes
0answers
11 views

Multiple integer output for neural network [closed]

I have a data set that contains 104 input features and 96 output values ​​to be predicted, the input features are floating values ​​normalized to [-1,1], and each out put value would be one integer ...
5
votes
1answer
45 views

Evaluating the performance of a machine learned recommendation system

I have a set of resumes $R=\{{r_1,...,r_n\}}$, which I've transformed to a vector space using TF-IDF. Each resume has a label, which is the name of their current employer. Each of these labels comes ...
1
vote
2answers
20 views

Difference between packaged sentiment analysis tools (TextBlob/NLTK) and training your own classifier?

I'm new to ML and training classifiers in practice, so I was just wondering what the difference was between the built-in sentiment tools of packages such as NLTK and TextBlob as compared to manually ...
1
vote
1answer
25 views

image classification with training set with 4 classes and test set with 3 classes

I have to do image classificaion with a CNN, and for doing this I have been given a training set with 4 classes and a test set with 3 classes. I am really confused because I don't know if this is ...
2
votes
1answer
21 views

What is the difference between all the different types of learning within machine learning?

This is a question that is really hard to google, and the differences are confusing. Does anyone have good examples of the differences between them all? Supervised Learning Semi-Supervised Learning ...
0
votes
2answers
38 views

Can some one please explain AI, Machine learning and Deep learning? [closed]

Can anybody Differentiate between AI, Machine-learning, and Deep-learning? Please Share if you have Detailed Material. Thanks in Advance.
3
votes
0answers
28 views

How do I interpret loss in a neural network?

I am studying how to evaluate the performances of a convolutional neural network, and in particular I have seen that we have to look both at accuracy and loss. I don't understand why do we have to ...
2
votes
0answers
25 views

Training an LSTM with different time steps and number of features

I want to use an LSTM using Keras to make course grade predictions. My dataset includes student transcripts, which consist of courses taken and their respective grades of students. For each course, I ...
1
vote
0answers
12 views

weighted quantile sketch in xgboost

I am unable to understand what is weighted quantile sketch in xgboost. Can anyone help me give an intuitive understanding of this?
0
votes
0answers
20 views

How to do Back Propagation Updation for below code?

Below is the code by Siraj Raval for implementing Neural Networks from Scratch. I have some doubts regarding the Code: Why during updation he did W2 = W2 + L1.T.dot(L2_Delta). I Mean shouldn't it be ...
2
votes
2answers
169 views

How to build an overfitted network in order to increase performances

I am learning how to implement CNN, and searching on the internet I have found that a trick to design a good network is to first build it in such a way that it overfits, and then use regularization to ...
1
vote
1answer
46 views

Anomaly detection - relation between thresholds and anomalies

I'm developing an anomaly detection program in Python. Main idea is to create a new LSTM model every day, training it with the previous 7 days and predict the next day. Then, using thresholds, find ...
1
vote
1answer
34 views

What does it mean the term variation for an image dataset?

I am working with convolutional neural networks, and I have seen that often we need to pre process the images before feeding them to the network. In particular, I have seen that often we have to do ...
2
votes
3answers
128 views

What is a channel in a CNN?

I was reading an article about convolutional neural networks, and I found something that I don' understand, which is: The filter must have the same number of channels as the input image so that the ...
0
votes
2answers
23 views

How to apply data binning on reviews data? [closed]

I need to apply data binning on a set of reviews, I have searched for some data binning methods for reviews and long-texts and couldn't find anything other than classification. Is NLP or ...
0
votes
1answer
22 views

Algorithm to match best nurses for a given shift [closed]

I'm the lead developer of a nursing startup. We want to match up nurses to a job, we want the best fit and best patient outcomes. We have nurses that have certain skills, ratings from hospitals and ...
1
vote
3answers
40 views

How do you predict a continuous variable when all your independent variables are categorical

I am new to data science and ML. Recently I have been given a sales dataset which contains weekly sales of a fashion brand. It has information about product like category(t shirt, polo shirt, cotton ...
0
votes
0answers
7 views

ResNet-Architecture 18 to 152 delivers same TPR and FPR

As I ve mentioned in the title. I am using all familiar ResNet-Architectures (18, 34, 50, 101, 152) for classifying two labels ('yes' or 'no') on base of two dimensional one-hot-encoded data (...
4
votes
1answer
40 views

Overfitting due to features correlating with training set generation rules

As background, I am using a Deep Neural Network built using Keras to classify inputs into 5 categories. The current structure of the network is: Input layer (~450 nodes) Dense layer (750 nodes) ...
1
vote
1answer
18 views

In Deep Learning, how many kinds of Attention exist? And what is the history of Attention models? [closed]

How many definitions of attention are commonly employed for Deep Learning tasks? That's what I've encountered up to now: Self-attention Bahdanau Luong Multi-Head (used in Transformers) Could you ...
1
vote
2answers
93 views

Training machine learning models from log files

Im starting to learn about ml and most of examples show very simple examples on how to train your ml modell. For me this looks more like statistic calculations than actual ml. These kind of examples ...
0
votes
0answers
12 views

Transformer Decoding in Inference mode for Time Series

With the Transformer model from "Attention is all you need" you have to feed in the the actual target during training. However, this can obviously not be done for actual inference. Now usually for ...
0
votes
2answers
29 views

How can I improve the results of my clustering

I am working on a project with the idea to cluster the sound waves of key strokes on a computer. So far what I have done was recorded about 50 keystrokes per key (only have done 1 - 10 so far), found ...
1
vote
1answer
11 views

When should we start using stacking of models?

I am solving a Kaggle contest and my single model has reached score of 0.121, I'd like to know when to start using ensembling/stacking to improve the score. I used lasso and xgboost and there ...
0
votes
0answers
14 views

How to consider different size of input for “Graph Conv Network”

I'm a student who just start study deep learning. I hope to practice with simple project using Graph Convolution Network. The question is that "How can I handle with different size of input graph ...
0
votes
1answer
23 views

Customer Intelligence - How to measure success?

we are creating models that aim to filter new leads from our current customer base. We started to create propensity models that calculate a percentage for each customer for a certain product group. I ...
2
votes
0answers
18 views

Implementing a Kernel Adaptive Filtering model explained in a paper

In this paper, Stock price prediction using kernel adaptive filtering within a stock market interdependence approach, the authors propose a method for predicting stock prices by combining the ...
1
vote
2answers
32 views

“Super” Optimizer concept

I was wondering why there isn't a feature built into common-use ML libraries, like Keras, that plugs many different combinations of layers and nodes to multiple models and trains them simultaneously ...
1
vote
1answer
39 views

How can we convert time series data to supervised learning problem?

I am preparing a data for machine learning model. I want to deal with time series data as normal supervised learning prediction. Let's say I have a data for car speed and I have several cars models ...
1
vote
1answer
27 views

When to use deep learning for java as opposed to python

I have been asked to explore options to build deep learning based applications using java, so i happend to browse a website called dl4j (https://deeplearning4j.org) which has got implemantations of ...
0
votes
1answer
27 views

Improve performances of a convolutional neural network

I am doing image classificaition, and to do this I have built the following neural network: ...
1
vote
2answers
31 views

Acceptable variation in accuracy of each k fold when using K-Fold Cross Validation?

I have a relatively small dataset consisting of 1432 samples. I have trained a Random Forest Classifier and performed KFold CV. The results of running 10 Fold CV are as follows: ...
0
votes
0answers
17 views

Math Behind GOSS (Gradient-Based One Side Sampling)?

As per my understanding through books & Google Search, GOSS (Gradient-Based One Side Sampling) is a novel sampling method that downsamples the instances on the basis of gradients. As we know ...
0
votes
0answers
5 views

Tensorflow SSD inception

Hi there I am new to tensorflow and I am just wondering how long does it usually take for my inception v2 model to recognise 50 objects in a picture. I usually leave my model run for 2000 steps and ...
4
votes
1answer
37 views

Naive Bayes implementation: why Laplace smoothing is different from theory?

Let's have a Naive Bayes Bernoulli classifier with $n_C$ classes and $n_F$ features. According to the formula in here and here and almost every theory book I could see, Laplacian smoothing means that ...
0
votes
0answers
10 views

How does setting preProcess argument in train function in Caret work?

I am trying to predict the times table training a neural network. However, I couldn't really get how preProcess argument works in ...
0
votes
0answers
13 views

when to use random forest over xgboost and vice versa [duplicate]

when to use randomforest over xgboost and vice versa? Based on precision and recall how we predict in kind if trees.
1
vote
1answer
18 views

Keras LSTM Input Shape - Batch Size and Time Step

So I have 82 different sets of data, each with varying length where each point has one feature and a label (0 or 1). I'm trying to use Keras LSTM to be able to predict the class of a point depending ...
1
vote
0answers
15 views
0
votes
1answer
23 views

How to gauge the Complexity of Pre trained Neural Networks?

What does one mean when they are talking about the simplicity of the networks? Does it mean that the shallower the networks the simpler they are, or does it mean that lesser the number of trainable ...
0
votes
0answers
11 views

Fragment level classification

Is there a tutorial or an example on fragment level classification task? I have to identify and classify specific n-grams in a text? The training data contains examples labeled as span or not span. (...
1
vote
0answers
11 views

Which non heuristic based approach would be best for document segmentation? [closed]

Due to my lack of knowledge in deep learning and neural network I need help picking the best approach to tackle a challenge. The problem I am trying to tackle is document segmentation using ...
5
votes
1answer
31 views

Chunking Sentences with Spacy

I have a lot of sentences (500k) which looks like this: ...
0
votes
0answers
9 views

how to use user KPI score data for making recommendations based on improving the performance

I have a dataset with these data points: user_id login_points meeting_complete points meeting_missed_points call_points lead_created_points and some features which tells the user activity and ...
2
votes
1answer
25 views

Does Feature Normalization affect Gradient Descent | Linear Regression

am new to datascience and i want to learn linear regression so i coded linear regression from scratch and performed gradient descent to find the best $w_\theta$ and $b_\theta$ values using a tutorial. ...
2
votes
1answer
27 views

Annotating the vocabulary using Word2vec model

I am trying to label the vocabulary in the corpus. I have trained the word2vec model on the corpus I have grouped the words which are related based on the score as key as the first word as the key ...
0
votes
1answer
17 views

Why seq2seq models are superior to simple LSTMs?

It is common knowledge in the field of Deep Learning that the most powerful Recurrent architecture is the sequence-to-sequence, or seq2seq, for pretty much any task (to time series forecasts, to ...
0
votes
1answer
34 views

PCA, why variance of eigen values is measure of its utility?

Source - Murphy, 12.3 Heuristic for assessing applicability of PCA. Let the empirical covariance matrix Σ have eigenvalues λ1≥λ2≥···≥λd>0, with mean λ. Explain why the variance of the eigen values, ...
1
vote
0answers
23 views

Detect blur image using ssdmobilenet and tensorflowlite

I have clear images of cards vs blurry images of card. My task is to capture photo when the image is not blurry, as you can see from the description I need this code to run in real time on android ...
1
vote
0answers
20 views

considerations on growing number of parameters in a neural network

I have built a convolutional neural network, in particular an AlexNet, and I have noticed that the number of parameters grow a lot as we go forward in the network. Now, I know that the parameters in ...