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
Join us in building a kind, collaborative learning community via our updated Code of Conduct.

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

0
votes
1answer
7 views

Down-sampling the data

I'm trying to do a regression analysis with two different datasets. One of them has 965 samples and the other 2275. I wish to downsample the latter to 965. Please suggest ways to do so. Thank you!
0
votes
1answer
10 views

High RMSE and MAE and low MAPE

I have used a few regression models on the same dataset and obtained error metrics for them as shown below, The RMSE(Root Mean Squared Error) and MAE(Mean Absolute Error) for model A is lower than ...
0
votes
1answer
15 views

When memory errors occur with model.fit(), is it due to GPU RAM or normal RAM?

With respect to this question, https://stackoverflow.com/questions/51895278/how-to-know-when-to-use-fit-generator-in-keras-when-training-data-gets-too-big when memory errors are reported due to ...
0
votes
0answers
3 views

Is it a good practice to always apply `ReduceLROnPlateau()`, given that models benefit from reducing learning rate once learning stagnates?

The rationale behind the keras function ReduceLROnPlateau() is that models benefit from reducing learning rate once learning stagnates. Is it a good practice to ...
2
votes
1answer
10 views

Is this a problem for a Seq2Seq model?

I'm struggling to find a tutorial/example which covers using an seq2seq model for sequential inputs other then text/translation. I have a multivariate dataset with n number of input variables each ...
1
vote
1answer
6 views

Predicting Composition of Chemical Compounds

I have a dataset which has names of compounds and their compositions. Like below Sulphuric Acid=>[H,S,O] (Hydrogen, sulphur, oxygen) Oxalic Acid=>[H,C,O] Sodium Oxalate=>[Na,C,O] Potassium Sulphate=>[...
1
vote
0answers
13 views

Determining nature of content in an article [on hold]

What is the general idea (in layman's terms without technical details) of knowing the nature of content of an article? For example: Whether an article is spam or promotional content, or is a fake news,...
2
votes
0answers
4 views

What would be the main and essential criteria for evaluating auto-sklearn library ?

I m running experiments using benchmark datasets with auto-sklearn to see how its performance is different to the standard sklearn library, Since automl does an exhaustive search over parameters and ...
2
votes
0answers
5 views

How to find coreset of a given dataset in python?

I am trying to implement the core-means algorithm, which is basically k-means using coreset. I have searched up and down but could not find any libraries or modules which could help me with this. ...
2
votes
0answers
15 views

Why is the derivative of the product of a vector and its transpose cTc2 c? [on hold]

I'm learning principal component analysis and i have to derive the result that will minimize the error $$c^* = \arg \min{[x-g(c)]^2} = \arg \min{[x-g(c)]^\mathsf{T}[x-g(c)]}$$. What I have done so ...
2
votes
0answers
9 views

Importance Sampling in Off-policy n-step Sarsa

In Chapter 7.3 of Reinforcement Learning: An Introduction by Sutton and Barto, the off-policy pseudocode has the following update equation for $Q$: Compute importance sampling ratio: $$ \rho \...
1
vote
0answers
12 views

Input data for this dataset to be feed into keras for training

Suppose I have 3 csv files which forms the dataset for training a machine learning model in Keras. file1.csv ...
1
vote
0answers
13 views

Improving the accuracy of my activity classifier

I'm extremely new to machine learning. I recently discovered turicreate and wanted to use it on a project to classify data spit out by the accelerometer and ...
0
votes
1answer
15 views

how to visualize InceptionV3 hidden layers

I am following google codelab: Tensorflow for poet to train my custom model. This google codelab use the Inception-V3 model for training. The inception-V3 model have 48 layer. My question is that ...
2
votes
1answer
19 views

What is wrong with this reinforcement learning environment ?

I'm working on below reinforcement learning problem: I have bottle of fix capacity (say 5 liters). At the bottom of bottle there is cock to remove water. The distribution of removal of water is not ...
3
votes
1answer
29 views

How can ReLU ever fit the curve of x²?

As far as I understand (pardon me if I am wrong) the activation functions in a neural network go through the following transformations: Multiplication by constants(weights) to x ( $f(ax)$ , $f(x)$ ...
0
votes
0answers
9 views

Source of Arthur Samuel's definition of machine learning

Many people seem to agree that Arthur Samuel wrote or said in 1959 that machine learning is the "Field of study that gives computers the ability to learn without being explicitly programmed". For ...
-1
votes
0answers
10 views

Using Orange to get more actionable Google Analytics insights? [on hold]

So i'm wondering if it's possible to use the Orange to get more actionable insights out of my Google Analytics data? And if so, how? #newbie
0
votes
0answers
23 views

how to check the classes the keras classifier/Neural Network is trained on?

I have trained a CNN using keras for Image classification with 3 classes. The results are bad and I'm trying to understand what the classifier has learnt and what it has not. It's only giving me an ...
2
votes
0answers
18 views

Deep Learning: Does starting the training on a smaller subset of the data make sense?

I trained a deep neural network with a small subset of my data, which allowed me to go through many epochs in a short amount of time and allowed the model to perform reasonably, then I gave it the ...
0
votes
2answers
20 views

Custom conditional Keras metric

I am trying to create the following metric for my neural network using keras $$ s = \left\{ \begin{array}{ll} \sum_{i=1}^{n} e^{\frac{-d_i}{10}}-1 & \quad d < 0 \\ ...
0
votes
0answers
8 views

How many interesting cases do I need in my sample for classification?

I'm trying to construct a binary classification model of a rare event. Let's say I have a sample of 1000 and have the option of dictating what degree of balance I have between both outcomes. What ...
0
votes
1answer
12 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
1answer
22 views

How to give rewards to actions in RL?

I'm working on below reinforcement learning problem: I have bottle of fix capacity (say 5 liters). At the bottom of bottle there is cock to remove water. The distribution of removal of water is not ...
2
votes
1answer
30 views

NLP - How to perform semantic analysis?

I'd like to perform a textual/sentiment analysis. I was able to analyse samples with 3 labels: (positive, neutral, negative) and I used algorithms such as SVM, ...
1
vote
0answers
16 views

Intuition / Importance of intermediate supervision in deep learning

These days, I have seen many papers using intermediate supervision. Single Network When using a single neural network, multiple neurons output predictions, perhaps by processing data in different ...
8
votes
4answers
2k views

Why does adding a dropout layer in Keras improve machine learning performance, given that dropout suppresses some neurons from the model?

If removing some neurons result in a better performing model, why not use a simpler neural network with fewer layers, fewer neurons in the first place? Why build a bigger, more complicated model in ...
0
votes
1answer
32 views

Interpretation & interpretability of machine learning models

What is the current status on the interpretation & general interpretability of machine learning models? Any links would be highly appreciated.
1
vote
0answers
12 views

Reinforcement algorithm for binary classification

I am new to machine learning, but I've read a lot about Reinforcement Learning in the past 2 days. I have an application that fetches a list of projects (e.g. from Upwork). There is a moderator that ...
1
vote
0answers
18 views

Deep Q-Learning with large number of actions

I'm using DQN with large number of actions in [0, 10000, step = 1000]. This means I have an action space of size 11 (including 0 and 10000). Action space is still discrete. My problem is that, instead ...
2
votes
2answers
24 views

Is it a good idea to normalize the outputs of a Neural Network for Regression, when the different outputs vary in magnitude?

I understood that it is not necessary to scale the output of a neural Network when I predict a single value via regression. Is it necessary do normalize the Outputs of my neural Network if I have ...
0
votes
1answer
9 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 ...
1
vote
1answer
12 views

How do you classify groups when the inputs are paired?

My data is like this: there is a choice between two alternatives and the customer chooses one. Each time the alternatives are different. I would like to characterize a desirable alternative. I don't ...
0
votes
1answer
9 views

Adding the input layer - units with a decimal

I took the course Machine Learning A-Z from Udemy and am trying to apply what I learned in the tutorials. Theye taught us in the "Adding the input layer" portion of an ANN that the units is based off ...
-2
votes
0answers
8 views

What information can be extracted from a homepage as features for detecting phishing websites?

I want to detect Phishing Websites using different Methods. But first I have to collect data, like for example the HTTP Header, or the HTML-Code. My Question is, what features can still be extracted ...
1
vote
0answers
8 views

Learning to parse elements from text and assigning them to categories

I am trying to generate a table with values parsed from unstructured text. Below are a couple of examples of possibly thousands of entries. For each entry, I would like to identify the title, assign ...
-1
votes
0answers
7 views

what is the technique to identify whether a text is a command or not with natural language processing?

We need to filter commands such as "Shut up" from utterances (which are in textual form). What is the technique to use for such tasks.
1
vote
0answers
15 views

How to determine the k in kNN [duplicate]

I'm looking to use the k-Nearest Neighbors (kNN) algorithm. What are the possible methods for determining the best K? From what I have read, looking at many different values(say 10-100) should work, ...
3
votes
1answer
20 views

Interpreting the Root Mean Squared Error (RMSE)!

I real all about pros and cons of RMSE vs. other absolute errors namely mean absolute error (MAE). See the the following references: MAE and RMSE — Which Metric is Better? What's the bottom line? How ...
0
votes
1answer
10 views

Simple question about prediction classes of item in question vs not item in question

Let's say I wanted to use transfer learning to train a model to detect object A vs everything else. In this case, do I provide 2 types of input, images of object A and images of everything else, and ...
1
vote
0answers
18 views

How can spatiotemporal population data be used for modeling migration?

I have a dataset that contains the population of butterflies(5 species) for 15 years for different locations. I want to model it against the climate index collected for same time period and location. ...
0
votes
0answers
11 views

What research is this similar to — Deep CNN for generating images by classifying individual pixels — not a GAN [on hold]

Generative adversarial models (GAN) use deconvolution to generate images (generator model) combined with convolution to distinguish between real and generated (determinator). However, multiple models ...
-1
votes
2answers
17 views

two dimensional list takes huge amount of memory

I have a 2d list which is created from lung CT image data and a label (the first item is a 3d array(image data) and the second item is a label(0 or 1)), I need this to data to train CNN model, the ...
2
votes
3answers
30 views

Decision tree where identical set of features results in different outcomes

I am following the example described in this page to test my decision tree program. The initial data set is ...
0
votes
0answers
8 views
1
vote
1answer
30 views

Evaluating metrics F1, F2, Mean Average Precision for object detection

Up today in the company where I work we are using the F1 Score for evaluating the performance of our model, also our competitor's using the same metric. I would like to understand what's the ...
2
votes
1answer
19 views

Difference between advantages of Experience Replay in DQN2013 paper

I've been re-reading the Playing Atari with Deep Reinforcement Learning (2013) paper. It lists three advantages of experience replay: This approach has several advantages over standard online Q-...
0
votes
0answers
11 views

How to define an anomaly detection problem?

I defined a supervised machine learning tasks as: Given: $m$ training examples with $n-1$ features: $E\in\mathcal{R}^{m\times (n-1)}$ and labels: $L \in \mathcal{R}^m$, a model $f$ of $d$ ...
3
votes
0answers
19 views

How to best estimate the coefficients of a confusion matrix in case of strong class imbalance?

I have a trained binary classifier (forget about how this was trained and think of it as a magical black box) and I would like to measure its classification performance (e.g. compute a confusion ...
0
votes
0answers
7 views

How to find correlation among multiple attributes in group by dataframe object?

I have a data frame with following attributes : CP - Counting point of vehicles A-Junction - Starting node of a road ...