Focused crawls are collections of frequently-updated webcrawl data from narrow (as opposed to broad or wide) web crawls, often focused on a single domain or subdomain.
Compendio de conocimiento sobre series temporales, para la predicción de series temporales con todos los métodos tratados en nuestro laboratorio DICITS.
Matrix-Vector Library Designed for Neural Network Construction. cuda (gpu) support, openmp (multithreaded cpu) support, partial support of BLAS, expression template based implementation PTX code generation identical to hand written kernels, and support for auto-differentiation
Mathematical consequences of orthogonal weights initialization and regularization in deep learning. Experiments with gain-adjusted orthogonal regularizer on RNNs with SeqMNIST dataset.
Handwriting Recognition and Generation with Long Short Term Memory Recurrent Neural Networks (based off https://github.com/Grzego/handwriting-generation) with better performance on longer inputs and made more accessible as a Flask web app
Won the 10 Days ML Challenge hosted by Tensorflow User Group Mumbai. This Repository consists of the problem statements and their solutions developed by me.
My first simple realization of Neural Network library by scratch, so you can use it in your projects (check the documentation in README). You can see an example how to use the library below.