In this article, we looked at the basic elements of an end-to-end Automatic Speech Recognition pipeline, the major challenges encountered with these pipelines, and some of the potential solutions.
In this article, we take a look at 1 x 1 convolution not only as a down-sampling tool, but also its many other potential uses with convolutional neural networks, such as dimensionality reduction or adding non-linearity.
In this article, we examine the effects of batch size on DL model training times and accuracies, and go on to describe a methodology for finding the maximum batch size for any given task.
We sit down with Tunebat and Specterr founder Oliver Reznik who is using machine learning to build powerful applications for DJs and musicians
In this blogpost, we endeavor to build a conceptual understanding of how exactly ProGANs work. We then proceed to build the network from scratch to generate facial structures
In this tutorial, we start by introducing techniques for extracting audio features from music data. We then show how to implement a music genre classifier from scratch in TensorFlow/Keras using those features calculated by the Librosa library.
In this tutorial, we discuss the history of image dehazing, show how to set an image dehazing task up in a notebook, and then examine 7 different techniques for performing image dehazing with deep learning!
In this tutorial, we examine the new YOLOv7 & its new features, learn how to prepare custom datasets for the model, and then build a YOLOv7 demo from scratch using NBA footage to detect and discern the ball handler from players on the court.
In this blog post, we learn how to build an unsupervised NLP pipeline for automatically extracting/generating glossaries and associated definitions from a given text document like a book/chapter/essay.
