Tag: Deep Learning

How Data Augmentation Improves your CNN performance? — An Experiment in PyTorch and Torchvision

From: https://medium.com/swlh/how-data-augmentation-improves-your-cnn-performance-an-experiment-in-pytorch-and-torchvision-e5fb36d038fb Simple ways to boost your network performance Credits: https://amanispas.co.za/wp-content/uploads/2019/12/AdobeStock_241822083-Web-Crop-1360x680.jpg In simple terms, Data Augmentation is simply creating fake data. You use the data in the existing train set to create variations of it. This does two things — Increases the size of your training setRegularizes your network The book Deep Learningdefines regularization as any method … Continue reading How Data Augmentation Improves your CNN performance? — An Experiment in PyTorch and Torchvision →

Deep Learning for Time Series Classification (InceptionTime)

From: https://towardsdatascience.com/deep-learning-for-time-series-classification-inceptiontime-245703f422db Fig. 1: The Inception module of InceptionTime. Index MotivationMachine Learning for Time Series ClassificationBest Deep Learning practices for Time Series Classification: InceptionTimeUnderstanding InceptionTimeConclusion 1. Motivation Time series data have always been of major interest to financial services, and now with the rise of real-time applications, other areas such as retail and programmatic advertising … Continue reading Deep Learning for Time Series Classification (InceptionTime) →

Deep Portfolio Optimization — An Experiment with Cryptocurrencies

From: https://towardsdatascience.com/deep-portfolio-optimization-an-experiment-with-cryptocurrencies-106bf22a634 Feeling bullish. Image source Ifyou’ve ever taken an intro finance or investment theory class, then you’ve probably come across the idea of Modern Portfolio Theory or MPT. The Nobel Prize winning idea is that we have a collection of assets which have different returns, risks and correlations with each other, and we find an optimal weighing … Continue reading Deep Portfolio Optimization — An Experiment with Cryptocurrencies →

Intuitively Understanding Convolutions for Deep Learning

From: https://towardsdatascience.com/intuitively-understanding-convolutions-for-deep-learning-1f6f42faee1 The advent of powerful and versatile deep learning frameworks in recent years has made it possible to implement convolution layers into a deep learning model an extremely simple task, often achievable in a single line of code. However, understanding convolutions, especially for the first time can often feel a bit unnerving, with terms … Continue reading Intuitively Understanding Convolutions for Deep Learning →

Solving Differential Equations and Kolmogorov Equations using Deep Learning

From: https://medium.com/nieuwsgierigheid/solving-differential-equations-and-kolmogorov-equations-using-deep-learning-c39aed011a10 This work seeks to make Beck et. al, 2018 understandable and put their solutions in a strong background to prepare for understanding of Stochastic Differential Equations. What are Stochastic Differential Equations? You’ve seen Ordinary Differential Equations. They are not spooky! They look like so: Equation 1: An Ordinary Differential Equation What defines an ordinary differential equation is … Continue reading Solving Differential Equations and Kolmogorov Equations using Deep Learning →

Using TensorFlow 2.0 to Compose Music

From: https://www.datacamp.com/community/tutorials/using-tensorflow-to-compose-music This tutorial was developed around TensorFlow 2.0 in Python, along with the high-level Keras API, which plays an enhanced role in TensorFlow 2.0. For those who would like to learn more about TensorFlow 2.0, see Introduction to TensorFlow in Python on DataCamp. For an exhaustive review of the deep learning for music literature, see Briot, Hadjerest, … Continue reading Using TensorFlow 2.0 to Compose Music →

Noise: It’s not always annoying

From: https://towardsdatascience.com/noise-its-not-always-annoying-1bd5f0f240f One of the first concepts you learn when you begin to study neural networks is the meaning of overfitting and underfitting. Sometimes, it is a challenge to train a model that generalizes your data perfectly, especially when you have a small dataset because: When you train a neural network with small datasets, the network generally memorizes … Continue reading Noise: It’s not always annoying →

Detecting Heart Arrhythmias with Deep Learning in Keras with Dense, CNN, and LSTM

From: https://towardsdatascience.com/detecting-heart-arrhythmias-with-deep-learning-in-keras-with-dense-cnn-and-lstm-add337d9e41f Let’s detect abnormal heart beats from a single ECG signal From: https://towardsdatascience.com/detecting-heart-arrhythmias-with-deep-learning-in-keras-with-dense-cnn-and-lstm-add337d9e41f Introduction Recently, I was reviewing Andrew Ng’s team’s work(https://stanfordmlgroup.github.io/projects/ecg/) on heart arrhythmia detector with convolutional neural networks (CNN). I found this quite fascinating especially with the emergence of wearable products (e.g. Apple Watch and portable EKG machines) that are capable of … Continue reading Detecting Heart Arrhythmias with Deep Learning in Keras with Dense, CNN, and LSTM →

Applied Topological Data Analysis to Deep Learning? Hands-on Arrhythmia Classification!

From: https://towardsdatascience.com/applied-topological-data-analysis-to-deep-learning-hands-on-arrhythmia-classification-48993d78f9e6 Healthcare is an exciting world to be working in. Every controlled performance enhancement somewhat means saving or improving lives. As a consequence, good enough generalization is not something you can get complacent about. Now comes the question of how to do it. Some do enhance their inference by augmenting the size of their … Continue reading Applied Topological Data Analysis to Deep Learning? Hands-on Arrhythmia Classification! →

Deploying your first Deep Learning Model: MNIST in production environment

From: https://towardsdatascience.com/deploying-your-first-deep-learning-model-mnist-in-production-environment-510bfdc4808d How you can deploy your MNIST model in production environment MNIST Dataset is a hello world dataset for most of the ML Enthusiast likes us. At some point everyone who has started their journey in this field or willing to start will come across this dataset and get their hands on for sure. It … Continue reading Deploying your first Deep Learning Model: MNIST in production environment →