6

Yes. For instance, the popular softmax regression gives you probability distribution for each class. Yes. Softmax is a regression over a set of discrete classes. We can use regression for classification, the most common strategy is to grab the most likely class for the prediction.


4

If your model is gradient-based, such as a neural network, then may also be able to use gradient methods to drive virtual inputs: Freeze all network weights to the trained version Define a loss function that decribes how you want the output - or any internal measure - to behave. E.g. to maximise the output, the loss function can simply be the negative of ...


4

I think it depends on you application and what data you have available. If the prediction of body temperature itself doesn't have to be accurate and classes like COLD, NORMAL, and HOT will suffice, you should stay with a classification. There isn't a cut off but as you increase the number of classes that represent numbers on the same scale, it may become ...


4

So in a sense you are correct. Using your jargon: linear regression will only "work" if the true function is approximately $y=h(x)=\beta^{T}x+\beta_0$. Advantages to using this is that its light, its convex, and all-around easy. but for alot of larger problems, this wont work. As you said you want the machine to do the work, so this is (kinda) where deeper ...


4

Any supervised learning problem can be cast as an equivalent reinforcement learning one. Suppose you have the training dataset $\mathcal{D} = \{ (x_i, y_i \}_{i=1}^N$, where $x_i$ is an observation and $y_i$ the corresponding label. Then let $x_i$ be a state and let $f(x_i) = \hat{y}_i$, where $f$ is your (current) model, be an action. So, the predicted ...


3

The main distinction between tasks is 'classification' vs 'regression'. In classification you would try to identify the presence of a cloud or not in an image, if you want to predict the level of 'cloudness' with continuous values you are then performing a regression task. I'm not aware about state-of-the models specific for images, but you can potentially ...


3

Of course, it's possible to define a problem where there is no relationship between input $x$ and output $y$. In general, if the mutual information between $x$ and $y$ is zero (i.e. $x$ and $y$ are statistically independent) then the best prediction you can do is independent of $x$. The task of machine learning is to learn a distribution $q(y|x)$ that is as ...


3

In reality GANs are not made for image classification, but for data generation, and they have gained popularity on image generation. They are also used for tabular data generation, see for example TGAN, or for time series generation, e.g. Quant GAN. You have even some application for the field of graphs and networking, e.g. NetGAN and GraphGAN.


3

The following graph shows the constraint region (green), along with contours for Residual sum of squares (red ellipse). These are iso-lines signifying that points on an ellipse have the same RSS. Figure: Lasso (left) and Ridge (right) Constraints [Source: Elements of Statistical Learning] As Ridge regression has a circular constraint ($|\beta_1| + |\...


3

When you define a straight line of the form $y=mx+c$, you need 2 points $(x_1,y_1)$ and $(x_2,y_2)$, to solve for the 2 variables $m$ and $c$ (you can easily visualise this graphically). Similarly, a parabola of the form $y=ax^2+bx+c$ will require 3 such points. Now viewing it as a ML problem, you are given the points and you have to estimate the parameters ...


2

See the blog post Why You Should Use Cross-Entropy Error Instead Of Classification Error Or Mean Squared Error For Neural Network Classifier Training (2013) by James D. McCaffrey. It should give you an intuition of why the average cross-entropy (ACE) is more appropriate than MSE (but MSE is also applicable). In a few words, $\tanh$ + MSE is like sigmoid + ...


2

Since you're termed the problem you're trying to solve is to "measure the body temperature of a person", the output should be a continuous valued number. If the problem statement had been to rank or classify a person's body temperature as fever/healthy, then this could be a classification problem. Deep learning employ neuron units at the output layer ...


2

Impossible to solve until you define an error measurement ( by example |R-R'| or (R-R')^2 ) and how this error changes when A, B and C change. Extreme example: R is random (unrelated to A, B, C values) but static. Given some values to A, B, C, you can only answer the value of R(A,B,C) if A,B,C was in the training set. R(A,B,C) is undefined if A,B,C was not ...


2

Just as a general remark, notice that technically we don't use the term "accuracy" for regression settings, such as yours - only for classification ones. If RMSE is 'in the units of the quantity being estimated', does this mean we can say: "The network is on average (1-SQRT(0.019))*100 = 86.2% accurate"? No. The advantage of the RMSE, as you have ...


2

You're probably looking for regression, either linear or non-linear, which usually refers to a set of methods that can be used to predict a continuous (or numerical) value (the value of the so-called dependent variable), given one or more possibly numerical values (the values of the independent variables). (The other common task is called classification, ...


2

This should be possible given the fact that ANNs have the ability to do the feature engineering and feature selection tasks by themselves. This means that given a lesser number of input parameters, the model will be able to generate and select additional features by itself. You will obviously not be able to understand or model these features manually. The ...


1

You should not limit yourself to sigmoid as activation function on the last layer. Usually you're normalizing your dataset, but when you're testing/evaluating the model you're applying the inverse of the scaling transformation to the predictions, so you could easily use tanh which is defined on [-1, 1]


1

You have a problem in your code, you want to use "sigmoid" in the last layer. Fot the code you are showin you are using linear activation in the last layer.


1

Yes, due the input, output being constrained between zero and one that would be the only viable activation function.


1

Just for clarification: your description (1 sample per minute) does not match the example data (far fewer data points which is understandable, but also two data points in one minute which contradicts the initial assertion.) If your actual measurements are like that you should first work on the sampling process to get reliable data. For creating predictions, ...


1

Some ideas out the top of my head: In the case of $dy/dx_2>0$ you could compute the gradient using the chain rule and limit the weights so that the constrain holds In the case of $y + x_5 + x_7 < K$ you could use a clipping function on the output layer?


1

Actually regression comes under the statistical analysis. As you know many business activity(decision making) relies in the previous trends that can be grabbed from the organizations transaction data. When regression is performed on those organizational data. One can understand what decision can be made. One could even simulate the different conditions when ...


1

You can not use error to reliably measure accuracy. Error is best used as a measure of how fast the model is currently learning. As an example, using different loss functions (cross entorpy vs MSE) results in massively different values for the error at similar accuracy. Also considering this, an error of 0.0000000001 quite often has lower validation set ...


1

You need to perform Hyperparameter Tuning to identify - Number of hidden layers. Number of neurons in each of the hidden layers. Dropout The activation function you use in each of your hidden layers. There parameters are only related to how you build your model. There are others that relate to training like batch size, number of epochs and so on. Your ...


1

Are applications available in which neural networks can be used outside of regression analysis for something different? Just to name a few out of the top of my head. Computer Vision Image Classification Image Segmentation Object Detection Image Generation Style Transfer Image Captioning Pose Estimation Natural Language Processing Machine Translation ...


1

So this is considered Ordinal Regression. There are many ways to model this type of data, generally in some form of regression setting. I do not recommend the softmax route because as you mentioned, there exists prebuilt correlation to the outputs. Some common ways to approach this (Note that im assuming your looking for methodologies that can be ...


1

Have a look at sklearn's sklearn.neural_network.MLPRegressor class, which uses a multi-layer neural network to do regression. You first need to define the object MLPRegressor, for example, by specifying the value of the parameter hidden_layer_sizes, which determines the number of layers and the number of neurons per layer, then you should call the method fit ...


1

Yes you can user either classification or regression according to your output requirement, If you want labeled output, like either available or not available then classification should be used. If you want the output in the form of % of availability then regression should be used.


Only top voted, non community-wiki answers of a minimum length are eligible