Hi, I'm Jorge Murillo,

About Me

Mathematician, Software Architect & Developer, Research Scientist on AI & Machine Learning. Lead iOS architect for a nationwide financial institution with several Apps and over 500 thousand users. Implemented Image Recognition applications like Obstacle Detection, Documents Capture, and OCR interpretation; also NLP projects involving Topic Modeling and Semantic Mapping.

Learning

For more information, have a look at my curriculum vitae .

  • Generalize a ML model using Regularization techniques; Tune batch size and learning rate for better model performance\rOptimize a ML model; Apply the concepts in TensorFlow code.
    Tensorflow Machine Learning Cloud Computing
  • Understanding of many different analytics methods, including linear regression, logistic regression, CART, clustering, and data visualization; How to implement all of these methods in R; Applied understanding of mathematical optimization and how to solve optimization models in spreadsheet software.
    R Analytic methods Data visualization
  • Supervised learning (parametric/non-parametric algorithms, support vector machines, kernels, neural networks); Unsupervised learning (clustering, dimensionality reduction, recommender systems, deep learning); Best practices in machine learning (bias/variance theory; innovation process in machine learning and AI).
    Logistic Regression Artificial Neural Network
  • Identify why deep learning is currently popular; Optimize and evaluate models using loss functions and performance metrics; Mitigate common problems that arise in machine learning; Create repeatable and scalable training, evaluation, and test datasets
    Tensorflow Bigquery Data Cleansing
  • Frame a business use case as a machine learning problem; Gain a broad perspective of machine learning and where it can be used; Convert a candidate use case to be driven by machine learning; Recognize biases that machine learning can amplify.
    Google Cloud Platform Bigquery
  • Intro to TensorFlow Google/Coursera
    Use the Keras Sequential and Functional APIs for simple and advanced model creation; Design and build a TensorFlow 2.x input data pipeline; Use the tf.data library to manipulate data and large datasets; Train, deploy, and productionalize ML models at scale with Cloud AI Platform
    Build Input Data Pipeline Keras Python
  • Write distributed machine learning models that scale in Tensorflow, scale out the training of those models; Convert raw data to features in a way that allows ML to learn important characteristics from the data and bring human insight to bear on the problem; Incorporate the right mix of parameters that yields accurate, generalized models and knowledge of the theory to solve specific types of ML problems. Experiment with end-to-end ML, starting from building an ML-focused strategy and progressing into model training, optimization, and productionalization with hands-on labs using Google Cloud Platform.
    Feature Engineering Cloud Computing Tensorflow
  • Feature Engineering Google/Coursera
    Compare the key required aspects of a good feature; Understand how to preprocess and explore features with Cloud Dataflow and Cloud Dataprep; Combine and create new feature combinations through feature crosses; Understand and apply how TensorFlow transforms features
    Tensorflow
  • Generalize a ML model using Regularization techniques; Tune batch size and learning rate for better model performance; Optimize a ML model; Apply the concepts in TensorFlow code.
    Cloud Computing Tensorflow

Projects

Build and Maintain the Mobile Architecture for all the iOS applications of the Bank; provide support for Development Teams during implementation to ensure the proper use of the Architecture Guidelines and other better-practices agreements in order to generate a coherent development ecosystem where all the applications share secure core components while still allowing for flexibility in the User Interface and Experience Layers

iOS Architecture Swift

(1) Implement Image Convolutional filters in C++ optimized to run on Android mobile processors. (2) Capture features using (1) [Using C++ OpenCV massive image processing on a Linux box] and uses them to design & train a Deep Learning model to detect a pre-determined image-class [using Keras+Tensorflow], export the model to be deployed on Mobile Devices. (3) Use the model produced on (2) and deploy it [using NDK + optimized C++ code] to reach real-time predictions running locally on the mobile device. (4) Develop an Android Application to capture images from the camera and present alerts based on predictions.

Android NDK C++ Convolutional Filters Neural Networks

Web-based OpenCV development designed & implemented to process images locally on the user mobile browser: Android & iOS. Capture of images using the phone camera; image pre-processing to optimize features capture; find out about object presence & position, then run an OCR process using tesseract, finishing with interpretation and processing of the data obtained

OpenCV Tesseract OCR Javascript Image Pre-processing Convolutional Filters

Open Source Projects

Github

NLP Books semantic mapping project

Github
nlp nlp-machine-learning nltk nltk-python

Netbeans project to work on cpp code

Github

Convolutional NN notes and examples for exposition

Github

Real Time image processing with a Sobel Filter using OpenCV SDK for Android

Github
android opencv real-time

Simple app to show basic usage of NDK

Github