Applied Machine & Deep Learning

What is Contextual AI?

  • Contextual AI is just that — not merely a single model addressing a question in isolation — but a holistic system working across a rich and diverse set of data, interpreting the signal in context of its surrounding, what came before, what comes after. It is this additional missing context which affords the intelligence and perspicacious insight, leading to true disruptive innovation.

What is Artificial Intelligence?

  • Artificial Intelligence (AI) refers to systems which can sense, reason, learn, recall and take action in response to their environment and prior experiences. While there is a lot of industry hype over the future benefits and very real risks of autonomous systems, companies today are making significant advances in the areas of assisted and augmented intelligence, as well as more traditional automation.

  • Machine Learning (ML) is a subset of artificial intelligence that provides systems with the ability to learn and improve from experience without being explicitly programmed.

  • Deep Learning (DL) is a sub-field of machine learning methods based on learning data representations, as opposed to task-specific algorithms. Learning can be supervised, semi-supervised, unsupervised and reinforcement based on performance feedback.

Photo by Paul Talbot on Unsplash

Photo by Paul Talbot on Unsplash

Use Cases

  • Feature Detection & Extraction

  • Recommender Systems

  • Anomaly & Pattern Detection

  • Predictive & Retrospective Analysis

  • Error, FMEA & Quality Analysis

  • Sentiment Analysis

Photo by Kristina Kermanshahche / Perspicace

Photo by Kristina Kermanshahche / Perspicace

Data Sources

  • Computer Vision & Image Analysis

  • Natural Language Processing (NLP)

  • Speech Recognition

  • Spatial Analysis

  • Sensor Data (IoT)

  • Structured & Unstructured Big Data

Algorithms

  • Linear & Logistical Regression

  • Binary & Multiclass Classification

  • Convolutional Neural Networks (CNNs)

  • Recurrent Neural Networks (RNNs)

  • Generative Adversarial Networks (GANs)

  • Support Vector Machines (SVMs)

  • K-Means Clustering, Principal Component Analysis (PCA)

  • Graph-based ML & Decision Trees