Introduction to this Blog:

Research interests include pattern analysis and machine intelligence. My machine learning programming focus is what I call "Reading the Robot Mind" which is closely related to "explainability." This ability to peer into the inner workings of trained inference engines is needed in order to spot intentional and unintentional bias, privacy violations, and performance bugs. The techniques discussed here relate to reverse processing of neural networks, so that example input data can be generated for different categories and classes. Similar to Generative networks, as well as Autoencoders, the premise is that a subject matter expert should be able to qualitatively assess the performance of a trained AI system, without the need for programming expertise.

Keywords include:

  • Pattern Analysis
  • Machine Intelligence
  • PAMI
  • Reading the Robot Mind
  • Mind Reading
  • Generative Networks
  • Generative Adversarial Netowrks
  • GAN
  • Autoencoder
  • Auto Encode
  • Subject Matter Expert
  • SME
  • Qualitative Analysis of Artificial Intelligence
  • Artificial Intelligence
  • AI
  • AI Assessment
  • Categorization
  • Classification
  • Machine Learning
  • Explainability
  • Classification
  • Image Processing
  • Pattern Recognition
  • Language
  • Computer Vision
  • Digital Signal Processing
  • Signal Processing
  • Feature Extraction
  • Signal Processing
  • Electrical Engineering
  • KNN
  • EEG
  • Neural Networks
  • Signal Analysis
  • Affective Learning
  • Affective Neuroscience
  • Visualization
  • Big Data
  • EEG Signal Processing
  • Information Visualization
  • Detection
  • Speech Recognition
  • Brain Signal Processing
  • Web Applications
  • User Interface
  • HTML
  • EEG Analysis
  • Semantic Analysis
  • Ensemble Inference
  • Configuration
  • Extensible Markup Languages
  • Signal Processing
  • Brain-Machine Interface
  • Neuromarketing
  • Speech Analysis
  • Markup Languages
  • Web Analytics
  • Adaptive Visualization

Programming

I am currently writing in C (posted on GitHub) and Keras using TensorFlow in Python posted on Kaggle from Google.
Location: Richmond, VA, USA

Comments

Post a Comment

Popular posts from this blog

Image
Reverse Inference Example Software:  This points to example software on GitHub where you can see some of these concepts in action. Here is the link: https://github.com/prof-nussbaum/Reverse_Inference  Reverse_Inference Working backwards through a deep convolutional network, to recreate the input image - and identify areas for improvement. Please see this article for more details on this technique, that I call "Reading the Robot Mind." https://readingtherobotmind.blogspot.com/2021/03/reading-robot-mind-deep-convolution.html What if we could read the robot's mind? It sounds like a silly statement, but if you could read a person's mind, you could "see" what they were thinking of when they mention a classification. If they say "I am seeing a dog" - reading their mind would give you additional details about the dog, or even perhaps, see what they are seeing. This is the same premise for Artificial Intelligence and Machine Learning. I know that deep conv...
Read more
Image
Auto-Associative How To - INCLUDING SOFTWARE CODE This repository includes "how to" examples of auto-associative neural networks. These networks have the ability to encode and decode (CODEC) sample data in the most efficient and low-loss way. The minimization of the loss function is accomplished through the use of gradient descent training algorithms. Example 1 - Auto-Associative How to (using TGS Salt Columns) The first "how-to" example comes from a competition held on the kaggle.com website. WHAT IS THE OVERARCHING GOAL? The competition, as well as details about the data set used for training, can be found here: https://www.kaggle.com/c/tgs-salt-identification-challenge . The purpose of the competition is to see who best can create an AI system that classifies seismic data. There are human experts who can do this classification from the original data, and indeed have done so to create the training and testing data. WHY USE AUTO-ASSOCIATIVE NETWORKS? In many case...
Read more
Auto-Encoder-CODEC This is a continuation of Auto-Encoder or Auto-Associative How To Examples This repository includes "how to" examples of auto-associative neural networks. These are sometimes called Auto-Encoders. These networks have the ability to encode and decode (CODEC) sample data in the most efficient and low-loss way. The minimization of the loss function is accomplished through the use of gradient descent training algorithms. Example 3 - MNIST Digit ConvAutoencoder This "how-to" example comes from a competition held on the kaggle.com website. WHAT IS THE OVERARCHING GOAL? Recognize handwritten digits from the MNIST dataset. Do it with CNN generated "features" or "encoded" version of the input - the center of an autoencoder. The subject matter expert (SME) can recognize digits. They qualitatively rate the amount of data lost due to encoded compression. If the SME can no longer make a classification from a decoded input, they qualitativel...
Read more