Ashok Chilakapati's repositories
Word-Embeddings-and-Document-Vectors
An evaluation of word-embeddings for classification
Bow-to-Bert
Evolution of word vectors from long, sparse, and 1-hot to short, dense, and context sensitive
Concept-Drift-and-Model-Decay
Evaluating model decay as the underlying concepts for classification evolve
BoW-vs-BERT-Classification
Comparing traditional classifiers with bag-of-words approach to BERT for text classification
ELK-Stack-with-Vagrant-and-Ansible
Building an ELK stack with Vagrant and Ansible
Kafka-Streams-Catching-Data-in-the-Act
An implementation of Kafka Streams
A-Flask-full-of-WSGI
Serving up python web applications has never been easier with the suite of WSGI servers at our disposal. Both uWSGI and gunicorn behind Nginx are excellent performers for serving up a Flask app…
context-aware-word-vectors
Context aware word vectors
Serving-Flask-on-Docker
Dockerizing a Flask web application behind gunicorn and Nginx
Clustering-text-with-tranformed-document-vectors
Clustering Text with Transformed Document Vectors
word-bags-vs-word-sequences-for-text-classification
Evaluating sequence respecting approaches like LSTM against traditional bag-of-words approaches for text
Attention-as-Dynamic-Tf-Idf-for-Deep-Learning
Implementing attention to recover task specific weighting of words
Choosing-the-Optimal-Number-of-Clusters-for-K-Means
Detecting the optimal number of clusters to use with K-means
computing-on-coupled-data-streams-with-Beam
Coupled data streams need to be analyzed together ensuring simultaneity of events across the participant streams
ELK-Clusters-on-AWS-with-Ansible
Building ELK Clusters on AWS with Ansible
Fracking-Features-in-Machine-Learning
Detecting data evolution and the need for new classes
Reconciling-Data-Shapes-and-Parameter-Counts-in-Keras
Deriving formulae for parameter counts when using convolutional layers
Virtual-Clusters-with-Vagrant-Virtualbox
Virtual Clusters with Vagrant & Virtualbox
ansible-filebeat
Ansible role for Filebeat
ansible-kibana
Ansible role for Kibana
ansible-logstash
Ansible role for Logstash
EasyBPY
A module to simplify the use of the Blender Python API.
elasticsearch-py
Official Python low-level client for Elasticsearch
Flowing-Tensors-and-Heaping-Parameters-in-Deep-Learning
Formulae for parameter counts in Dense, Embedding, LSTM and GRU layers