eonu

Resources on Gaussian Processes

Gaussian processes (GPs) are a challenging area of Bayesian machine learning to get started with – from wrapping your head around dealing with infinite dimensional Gaussian distributions, to understanding kernel functions and how to choose the right one for the right task, all on top of having solid knowledge of Bayesian inference.

While primarily used as a powerful regression model with the ability to estimate uncertainty in predictions, GPs can also be used for classification, and have a very wide range of applications.

These are some of the resources I have used, or are planning to use in my on-going process of learning about GPs.

Lectures

eonu

DeepGRU

A modular PyTorch implementation of the DeepGRU (Deep Gesture Recognition Utility) recurrent neural network architecture designed by Maghoumi & LaViola Jr.^[1], originally for gesture recognition but applicable to general sequences.

Dependencies

This implementation of DeepGRU requires a working installation of torch.

Usage

eonu

# ================================================================================= #
#         viewr: Better R object inspection using the FireFox JSON viewer.          #
# --------------------------------------------------------------------------------- #
# Usage:                                                                            #
#   Rscript viewr.R [FILE]       # Where [FILE] has extension .Rdata or .rds        #
#                                                                                   #
# This script will only work on macOS, and assumes that you have FireFox installed! #
# --------------------------------------------------------------------------------- #
#                            Edwin Onuonga (eonu) 2020                              #   
# ================================================================================= #

eonu

conda create -n ml python=3.7.4 \
  tensorflow tensorflow-datasets \
  pytorch torchvision cudatoolkit=10.2 \
  librosa torchaudio \
  numpy scikit-learn scipy pandas \ 
  matplotlib seaborn \ 
  nltk \ 
  pomegranate \
  jupyter \
  requests \

eonu

• Audio Classification Using CNN — An Experiment (Medium)
• A Joint Separation-Classification Model for Sound Event Detection of Weakly Labelled Data (ResearchGate)
• Spectrogram + convolution = ? (Kaggle)
• Towards End-to-End Speech Recognition with Deep Convolutional Neural Networks (arXiv)
• Deep Scalogram Representations for Acoustic Scene Classification

Other:

• Jupyter Audio Basics
• Jupyter Notebooks on GitHub Pages

eonu

#!/usr/bin/env ruby

class NBX
  # Execute long-running Jupyter notebooks from the command-line

  def initialize
    @allow_errors = true
    @inplace = false
  end

eonu

require 'active_record'

ENV['DATABASE_URL'] ||= "sqlite3:///path/to/db.sqlite3"
ActiveRecord::Base.establish_connection ENV['DATABASE_URL']

ActiveRecord::Schema.define do
  self.verbose = true
  
  create_table(:users, force: true) do |t|
    t.string :username, null: false, unique: true