# Tag Info

## New answers tagged machine-learning

0

I found a solution to this some time back. I have been studying function approximation (within linear regression) for some time. Here's how I did it: Neural Networks have been proved to be universal function approximators. So, even a single hidden layer would be sufficient to approximate a function simple as addition (Even somewhat complex functions like ...

3

As a rule of thumb, mean squared error (MSE) is more appropriate for regression problems, that is, problems where the output is a numerical value (i.e. a floating-point number or, in general, a real number). However, in principle, you can use the MSE for classification problems too (even though that may not be a good idea). MSE can be preceded by the ...

0

random forest's feature importances are not reliable and you should probably avoid them. Instead you can use permutation_importance: https://scikit-learn.org/stable/auto_examples/inspection/plot_permutation_importance.html#sphx-glr-auto-examples-inspection-plot-permutation-importance-py

2

This question is very broad, so let me attempt to answer it using my own background in time series analysis. As an example, why would I continue using ARIMA to forecast a time series? Why not simply use an LSTM model by default, since this is a type of recurrent neural network that takes time-related dependencies into account? Well, an LSTM model is not ...

1

Why are still traditional machine learning (ML) models used over neural networks if neural networks seem to be superior to traditional ML models? Of course, the model that achieves state-of-the-art performance depends on the problem, available datasets, etc., so a comprehensive comparison between traditional ML models and deep neural networks is not ...

0

The task of isolating 2 or more speakers is called speaker diarization, here a list of softwares and useful resources. Once you have the 2 or more audio files containing the individual voices, you could run some speech-to-text network that also outputs time information.

0

You would need to perform some kind of speech-to-text to get the audio transcription with the corresponding synchronization wrt the audio. Then search in the transcription. You could use DSAlign by mozilla

7

I'm going to use slightly different notation, $\leftarrow$ for an assignment, $\alpha$ for learning rate, $\nabla_w J$ in place of $g$* and implied multiplication as these are slightly more common. Also, using bold letters to represent vectors. In that notation, the update rule for basic gradient descent would be written as: $$\mathbf{w} \leftarrow \mathbf{... 1 If is a truly a random number, and you could guess each of the next successive five in sequence, then you could win the lottery consistently. This is one of the first tasks many people try to do when first learning machine learning. If the lottery is truly a random physical process with fair, i.e., balanced ping pong balls, then you cannot predict which ... 2 Well, the way to know that the agent is actually learning is by looking at its behavior while it performs the task, and by comparing against a known optimal performance. So, does your agent reaches the goal quickly? Does it step out of the grid frequently? What is the maximum possible sum of rewards / minimum number of steps attainable? Is the agent close ... 0 But because the inputs have to have a fixed length Do they? Why? The go-to strategy would be to use an RNN (possibly with LSTM or GRUs, but probably not necessary) and train it to process input sequentially and output the final classification of the paragraph. This has the advantage of being able to take into account word order and constellations, as ... 0 I am watching the same course too, and I think that in the example graph, the cost function is not a sum of MSE (Mean squarred errors), but it could be a cubic one, so a sum of cubical errors, and thus the cost function could be negative: as there are a variety of cost functions, the MSE ones are not adapted for every problems, and other formulations could ... 2 Summing up a sequence of word vector maybe used in practice sometimes. However, the operation of addition is non-reversible, meaning that once you sum up a few numbers, you cannot get the original numbers back. However summing up a sequence of word vectors may work depending on your task. You should also normalize the values, or just use average value. For ... 2 Yes this is possible, using any machine learning approach that supports regression. You have two main approaches: Input h the height of the drop, multiple outputs, one per time offset that you want to plot. Each individual output calculates the predicted force at a specific offset time. Inputs h the height of the drop and t a time offset, one output. ... 1 First of all, there are multiple factors on how well models will work. Amount of data, source of data, hyperparameters, model type, training time etc... All of these will affect the accuracy. However, no classifier will work best in general. It all depends on the different factors, and not one can satisfy all, at least for now. For improving the accuracy, ... 1 The accuracy depends on various factors. Might not always be the algorithm. For example a cleaner data with a poor algorithm might still give better results and vice versa. What are the preprocessing techniques you are using? This preprocessing techniques article is a good starting point for html data. And by vectorising I assume you mean word2vec, use a ... 1 l_{2,1} is a matrix norm, as stated in this paper. For a certain matrix A \in \mathbb{R}^{r\times c}, we have$$||A||_{2,1} = \sum_{i=1}^r \sqrt{\sum_{j=1}^c A_{ij}^2}$$You first apply l_2 norm along the columns to obtain a vector with r dimensions. Then, you apply l_1 norm to that vector to obtain a real number. You can generalize this notation ... 1 In reallity any continous function on a compact can be approximated by a neural network having one hidden layer with a finite number of neurones (This is the Universal Approximation Theorem). Thus you only need one hidden layer to approximate the multiplication on a compact, note that you need to apply a non linear activation on the hidden layer to do this. 0 A fairly recent paper posits an answer to this: Reconciling modern machine learning practice and the bias-variance trade-off. Mikhail Belkin, Daniel Hsu, Siyuan Ma, Soumik Mandal https://arxiv.org/abs/1812.11118 https://www.pnas.org/content/116/32/15849 I'm probably not qualified to summarize, but it sounds like their conjectured mechanism is: by having ... 2 A neural network is composed of continuous functions. Neural networks are regularized by adding an l2 penalty on the weights to the loss function. This means the neural network will try to make the weights as small as possible. The weights are also initiallized with a N(0, 1) distribution so the initial weights will also tend to be small. All of this means ... 1 Google has an API you can use. https://cloud.google.com/translate/. Their API can translate audio to text. They also have an API for converting speech to text. The language detection feature should let you detect the language in the resulting text. They have client libraries for the most popular programming languages. 0 There is normally more to generalisation than just increasing training data. It helps to make the task noisy, through various means. One common and popular method is to use dropout, which encourages the network to utilise every node, and avoids dependencies on small clusters of nodes. So how does making the task more noisy help with generalisation? Well it'... 3 Some other details you could mention are: total number of model parameters (e.g. 1.2M or 0.15M) & depth of the network (e.g. 38-layered network) family/style of the network architecture (e.g. encoder-decoder arch., LSTM) specifics of connections between network layers (e.g. residual-, dense-, skip-connections) specifics of individual components of the ... 0 Find some opensource projects like Arxiv sanity by andrej karpathy which finds ML related papers from arxiv.org. You can find similar opensource applications. 0 Welcome to the mine-field of semantic definitions within AI! According to Encyclopedia Britannica ML is a “discipline concerned with the implementation of computer software that can learn autonomously.” There are a bunch of other definitions for ML but generally they are all this vague, saying something about “learning”, “experience”, “autonomous”, etc. in ... 2 The difference is simply that non-linear regression learns parameters that in some way control the non-linearity - e.g. any weight or bias that is applied before a non-linear function. For instance:$$y = (w_1 x_1 + w_2 x_2)^2 + w_3 With such a function to learn, you cannot separate out transformed values of $w_1$ and $w_2$ and turn this into a linear ...

0

You are using Dense layers, try 1d convolution instead. Have you tried a different activation function such as softmax and instead of Binary cross entropy try MSE loss? Are all your inputs between 0 and 1? Also, I think your noise amplitude is too much in 2nd and 3rd case as compared to the actual signal. Can you try training on different types of spectra ...

Top 50 recent answers are included