PRIMO.ai

Overview

• How do I leverage AI?
• Courses
• Reading Material

Background

• What is AI?
• History of AI
• Current State

AI Breakthroughs

• Case Studies
• Capabilities
• AI Patents after 2013

AI Fun

• Google AI Experiments
• TensorFlow Playground

How to...

• AI Solver
• Strategy & Tactics
• Checklists

Forward Thinking

• Moonshots
• Journey to Singularity
• Creatives

Algorithms

• About Algorithms & Neural Network Models

Supervised

Labeled (desired solution) data is fed into the algorithm

• ...predict values
  • Linear Regression
  • Bayesian Linear Regression
  • Support Vector Regression (SVR)
  • Ordinal Regression
  • Poisson Regression
  • Tree-based...
    • Fast Forest Quantile Regression
    • Decision Forest Regression
  • Boosted Decision Tree Regression
  • General Regression Neural Network (GRNN)

• Anomaly Detection ...find outliers
  • One-class Support Vector Machine (SVM)
  • Principal Components Analysis (PCA)-based Anomaly Detection

• Classification ...predict categories
  • Perceptron (P)
  • Support Vector Machine (SVM)
  • Logistic Regression
  • Naive Bayes
  • Tree-based...
    • Boosted Decision Tree
    • Decision Forest
    • Decision Jungle
  • Feed Forward Neural Network (FF or FFNN)
  • Artificial Neural Network (ANN)
  • Deep Neural Network (DNN)

• Other
  • Hopfield Network (HN)
  • Energy-based Model (EBN)
  • Markov Model (Chain, Discrete Time, Continuous Tme, Hidden)

Convolutional

• (Deep) Convolutional Neural Network (DCNN/CNN)
• (Deep) Residual Network (DRN) - ResNet

Deonvolutional

• Deconvolutional Neural Network (DN) / Inverse Graphics Network (IGN)

Sequence

• Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and Recurrent Neural Network (RNN)
• Attention Model
• Sequence to Sequence (Seq2Seq)
• (Tree) Recursive Neural (Tensor) Network (RNTN)
• Neural Turing Machine

Unsupervised

Some uses of Unsupervised Learning are (1) data compression, (2) classification, (3) clustering, and (4) outlier detection

Unsupervised: Probabilistic/Generative

A probability distribution over a set of classes for each input sample. Unlabeled data is classified as (1) conditional probability of the target Y, or (2) conditional probability of the observable X given a target Y

• Clustering
  • K-Means
  • Mean-Shift Clustering
  • Density-Based Spatial Clustering of Applications with Noise (DBSCAN)
  • Expectation–Maximization (EM) Clustering using Gaussian Mixture Models (GMM)

• Hierarchical to include clustering
  • Hierarchical Cluster Analysis (HCA)
  • Hierarchical Clustering; Agglomerative (HAC) & Divisive (HDC)
  • Hierarchical Temporal Memory (HTM)

• Other
  • Restricted Boltzmann Machine (RBM)
  • Deep Belief Network (DBN)
  • Variational Autoencoder (VAE)

Competitive

• Generative Adversarial Network (GAN)
• Kohonen Network (KN)/Self Organizing Maps (SOM)

Unsupervised: Non-Probabilistic

Unlabeled data is fed into the algorithm with the algorithm seperating the feature space and return the class associated with the space where a sample originates from.

• Autoencoder (AE) / Encoder-Decoder
• (Stacked) Denoising Autoencoder (DAE)
• Sparse Autoencoder (SAE)

Semi-Supervised

• Semi-Supervised Learning with Generative Adversarial Network (SSL-GAN)
• Context-Conditional Generative Adversarial Network (CC-GAN)

Reinforcement (RL)

An 'agent' algorithm receives a delayed reward in the next time step to evaluate its previous action; in combination with Neural Networks it is capable of solving more complex tasks

• Markov Decision Process (MDP)
• Deep Reinforcement Learning (DRL)
• Deep Q Learning (DQN)
• Neural Coreference
• State-Action-Reward-State-Action (SARSA)
• Deep Deterministic Policy Gradient (DDPG)
• Trust Region Policy Optimization (TRPO)
• Proximal Policy Optimization (PPO)

Frameworks

• Frameworks Overview
• Frameworks and libraries in addition to TensorFlow

TensorFlow

• TensorFlow Overview & Tutorials
• TensorBoard
• TensorFlow.js
• TensorFlow Playground
• TensorFlow Lite
• TensorFlow Serving
• Related...
  • Keras
  • TFLearn
  • Swift

Techniques

Mathematical Background

• Math for Intelligence

Datasets & Information Analysis

• Datasets
• Data Preprocessing & Feature Exploration

Algorithms

• Backpropagation
• Repositories & Other Algorithms

Bag of Tricks

• Activation Functions
• Optimizers
  • Backpropagation
  • Gradient Descent Optimization & Challenges
  • Parameter Initialization
  • Choosing the Right Metric for Evaluating Machine Learning Models
  • Approach to Bias and Variances
• Pooling
• Hyperparameters
• Visualization
• Transfer Learning
• Competitions

Coding

• Javascript
• Python
• Other Coding options
• Jupyter Notebooks

Platforms: Machine Learning as a Service (MLaaS)

• Service Capabilities
• Other Platforms

Amazon AWS

• AWS with TensorFlow
• AmazonML
• Deep Learning Amazon Machine Image (DLAMI)
• DeepLens - deep learning enabled video camera
• AWS Training and Certification

Google Cloud AI

• Google Cloud AI With TensorFlow
• ML Engine
• Prediction API
• Google Developers Codelabs
• Google AI Experiments
• Cloud Vision API - drag & drop picture on webpage
• Learn from ML experts at Google

Kaggle

• Kaggle Overview
• Kaggle Kernels
• Kaggle Competitions
  • Passenger Screening
• Hands-On Data Science Education

Microsoft Azure

• Azure Process
• Azure with TensorFlow
• ML Studio
• Cognitive Services
• AI School

Research & Development

• Self Learning Artificial Intelligence - AutoML & World Models
• Explainable Artificial Intelligence
  • Adversarial Threats
• Differentiable Neural Computer (DNC)
• Genetic Algorithms
• Natural Language Inference (NLI) and Recognizing Textual Entailment (RTE)
• 3D Simulation Environments
• Connecting Brains
• Architectures
  • Deep Distributed Q Network Partial Observability
  • Capsule Networks (CapNets)
  • Generative Agents
  • Messaging & Routing
  • Processing Units - CPU, GPU, TPU, VPU
• Cybersecurity
• Other Challenges

Other

• Business-Centric Methodology
• Getting Started - MediaWiki