PRIMO.ai

On Friday April 19, 2024 PRIMO.ai has 736 pages

Getting Started

Overview

• How do I leverage AI?
• Courses & Certifications
• Reading Material & Glossary

Background

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

AI Breakthroughs

• Capabilities
• Case Studies
• AI Patents after 2013

AI Fun

• Google AI Experiments
• TensorFlow Playground
• TensorFlow.js Demos
• Google AIY Projects Program - Do-it-yourself artificial intelligence
• NVIDIA Playground
• Try GPT-2...Talk to Transformer - completes your text. | Adam D King, Hugging Face and OpenAI
• Competitions

How to...

• AI Solver for determining possible algorithms for your needs
• Strategy & Tactics for developing applications
• Checklists for ensuring consistency and completeness

Forward Thinking

• Moonshots
• Journey to Singularity
• Creatives

Information Analysis

• Framing Context
• Datasets
• Imbalanced Data
• Data Preprocessing
• Data Augmentation, Data Labeling, and Auto-Tagging
• Feature Exploration/Learning
• Batch Norm(alization) & Standardization
• Hyperparameters
• Zero Padding
• Train, Validate, and Test
• Model Assessment:
  • Choosing the Right Metric for Evaluating Machine Learning Models
  • Approach to Bias and Variances
  • Evaluation Measures - Classification Performance
  • Explainable Artificial Intelligence (XAI)
• Visualization
• Master Data Management (MDM) / Feature Store / Data Lineage / Data Catalog
• Data Interoperability

Algorithms

• Model Zoos

Predict values - Regression

• Linear Regression
• Ridge Regression
• Lasso Regression
• Elastic Net Regression
• Bayesian Linear Regression
• Logistic Regression (LR)
• Support Vector Regression (SVR)
• Ordinal Regression
• Poisson Regression
• Tree-based...
  • Fast Forest Quantile Regression
  • Decision Forest Regression
• General Regression Neural Network (GRNN)
• One-class Support Vector Machine (SVM)
• Gradient Boosting Machine (GBM)

Classification ...predict categories

• Supervised
  • Naive Bayes
  • K-Nearest Neighbors (KNN)
  • Perceptron (P) ...and Multi-layer Perceptron (MLP)
  • Feed Forward Neural Network (FF or FFNN)
  • Artificial Neural Network (ANN)
  • Deep Learning - Deep Neural Network (DNN)
  • Kernel Approximation - Kernel Trick
    • Support Vector Machine (SVM)
  • Logistic Regression (LR)
    • Softmax Regression; Multinominal Logistic Regression
  • Tree-based...
    • (Boosted) Decision Tree
    • Random Forest (or) Random Decision Forest
    • Decision Jungle
  • Apriori, Frequent Pattern (FP) Growth, Association Rules/Analysis
  • Markov Model (Chain, Discrete Time, Continuous Time, Hidden)
• Unsupervised
  • Radial Basis Function Network (RBFN)
  • Autoencoder (AE) / Encoder-Decoder
  • (Stacked) Denoising Autoencoder (DAE)
  • Sparse Autoencoder (SAE)

Recommendation

• Alternating Least Squares (ALS)
• Matrix Factorization

Clustering - Continuous - Dimensional Reduction

• Singular Value Decomposition (SVD)
• Principal Component Analysis (PCA)
• K-Means
• Fuzzy C-Means (FCM)
• K-Modes
• Association Rule Learning
• Mean-Shift Clustering
• Density-Based Spatial Clustering of Applications with Noise (DBSCAN)
• Expectation–Maximization (EM) Clustering using Gaussian Mixture Models (GMM)
• Restricted Boltzmann Machine (RBM)
• Variational Autoencoder (VAE)
• Biclustering
• Multidimensional Scaling (MDS)

Hierarchical

• Hierarchical Cluster Analysis (HCA)
• Hierarchical Clustering; Agglomerative (HAC) & Divisive (HDC)
• Hierarchical Temporal Memory (HTM) Time
• Mixture Models; Gaussian

Convolutional

• (Deep) Convolutional Neural Network (DCNN/CNN)
• (Deep) Residual Network (DRN) - ResNet
  • ResNet-50

Deconvolutional

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

Graph

- includes social networks, sensor networks, the entire Internet, 3D Objects (Point Cloud)

• Graph Convolutional Network (GCN), Graph Neural Networks (Graph Nets), Geometric Deep Learning
• Point Cloud
• A hierarchical RNN-based model to predict scene graphs for images
• A multi-granularity reasoning framework for social relation recognition
• Neural Structured Learning (NSL)

Sequence / Time

• Sequence to Sequence (Seq2Seq)
• End-to-End Speech
• Neural Turing Machine
• Recurrent Neural Network (RNN)
  • Long Short-Term Memory (LSTM)
  • Gated Recurrent Unit (GRU)
  • Bidirectional Long Short-Term Memory (BI-LSTM)
  • Bidirectional Long Short-Term Memory (BI-LSTM) with Attention Mechanism
  • Average-Stochastic Gradient Descent (SGD) Weight-Dropped LSTM (AWD-LSTM)
• (Tree) Recursive Neural (Tensor) Network (RNTN)

Time

• Temporal Difference (TD) Learning
• Predict values
  • Time Series Forecasting Methods - Statistical
  • Time Series Forecasting - Deep Learning

Spatialtemporal

Spatial-Temporal Dynamic Network (STDN)

Competitive

• Generative Adversarial Network (GAN)
• Conditional Adversarial Architecture (CAA)
• Kohonen Network (KN)/Self Organizing Maps (SOM)
• Quantum Generative Adversarial Learning (QuGAN - QGAN)

Semi-Supervised

In many practical situations, the cost to label is quite high, since it requires skilled human experts to do that. So, in the absence of labels in the majority of the observations but present in few, semi-supervised algorithms are the best candidates for the model building. These methods exploit the idea that even though the group memberships of the unlabeled data are unknown, this data carries important information about the group parameters.

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

Natural Language

• Natural Language Processing (NLP) involves speech recognition, (speech) translation, understanding (semantic parsing) complete sentences, understanding synonyms of matching words, and sentiment analysis
  • Current State of the Art:
    • Attention Mechanism/Model - Transformer Model
      • Generative Pre-trained Transformer-2 (GPT-2) ..Talk To Transformer
      • Bidirectional Encoder Representations from Transformers (BERT)
      • XLNet extends Transformer-XL
    • (Deep) Convolutional Neural Network (DCNN/CNN)
    • Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and Recurrent Neural Network (RNN)
  • Methods:
    • Text Preprocessing
      • Regular Expressions (Regex)
      • Soundex
      • Tokenization / Sentence Splitting
        • Word Embeddings
      • Normalization
        • Stemming (Morphological Similarity)
        • Lemmatization
      • Similarity
        • Word Similarity
        • Text Clustering
        • Sentence/Document Similarity
        • Text Classification
        • Topic Modeling
      • Whole Word Masking
      • Identity Scrubbing
      • Stop Words
    • Relating Text
      • Part-of-Speech (POS) Tagging
      • Chunking - chunks or patterns, e.g. telephone number
      • Chinking - unwanted chunk removal
      • Named Entity Recognition (NER)
      • Relation Extraction
      • Neural Coreference
  • Natural Language Understanding (NLU) or Natural Language Interpretation (NLI)
    • Managed Vocabularies
      • Corpora
      • Ontologies and Taxonomies
    • Natural Language Inference (NLI) and Recognizing Textual Entailment (RTE)
      • Semantic Role Labeling (SRL)
    • Deep Learning Algorithms
    • Capabilities
      • Summarization
      • Sentiment Analysis
      • Wikifier
    • Workbench / Pipeline
• Natural Language Generation (NLG) involves writing/generating complete grammatically correct sentences and paragraphs

Reinforcement Learning (RL)

an algorithm receives a delayed reward in the next time step to evaluate its previous action. Therefore based on those decisions, the algorithm will train itself based on the success/error of output. In combination with Neural Networks it is capable of solving more complex tasks. Policy Gradient (PG) methods are a type of reinforcement learning techniques that rely upon optimizing parametrized policies with respect to the expected return (long-term cumulative reward) by gradient descent.

• Monte Carlo (MC) Method - Model Free Reinforcement Learning
• Markov Decision Process (MDP)
• Q Learning
• State-Action-Reward-State-Action (SARSA)
• Deep Reinforcement Learning (DRL) DeepRL
• Distributed Deep Reinforcement Learning (DDRL)
• Deep Q Network (DQN)
• Evolutionary Computation / Genetic Algorithms
• Actor Critic
• Hierarchical Reinforcement Learning (HRL)

Neuro-Symbolic

the “connectionists” seek to construct artificial neural networks, inspired by biology, to learn about the world, while the “symbolists” seek to build intelligent machines by coding in logical rules and representations of the world. Neuro-Symbolic combines the fruits of group.

• Neuro-Symbolic Concept Learner (NS-CL)

Other

• Hopfield Network (HN)
• Energy-based Model (EBN)
• Generative Query Network (GQN)

Techniques

• Math for Intelligence
  • Statistics for Intelligence
  • Finding Paul Revere
• Arxiv Sanity Preserver to accelerate research

Methods & Concepts

• Backpropagation
• Overfitting Challenge
  • Regularization
  • Dropout
• Dimensional Reduction; identification - what influences an observed outcome
• Activation Functions
• Memory
  • Memory Networks
  • Attention Mechanism/Transformer Model
  • Transformer-XL
• Multiclassifiers; Ensembles and Hybrids; Bagging, Boosting, and Stacking
• Optimizers
  • Optimization Methods
  • Objective vs. Cost vs. Loss vs. Error Function
  • Gradient Descent Optimization & Challenges
  • Parameter Initialization
• Neural Network Pruning
• Repositories & Other Algorithms
• DAWNBench An End-to-End Deep Learning Benchmark and Competition
• Knowledge Graphs
• Quantization
• Causation vs. Correlation
• Object Detection; Faster R-CNN, YOLO, SSD
• Deep Features
• Local Features

Advanced Learning

• Text Transfer Learning
• Image/Video Transfer Learning
• Few Shot Learning
• Transfer Learning a model trained on one task is re-purposed on a second related task
• Ensemble Learning
• Multi-Task Learning (MTL)
• Apprenticeship Learning - Inverse Reinforcement Learning (IRL)
• Imitation Learning
• Simulated Environment Learning
• Lifelong Learning - Catastrophic Forgetting Challenge
• Neural Structured Learning (NSL)

Opportunities & Challenges

• Generative Modeling
• Inside Out - Curious Optimistic Reasoning
• Nature
  • Evolutionary Computation / Genetic Algorithms
  • Bio-inspired Computing
• Connecting Brains
  • Molecular Artificial Intelligence (AI)
  • Neuroscience
• Architectures
  • Deep Distributed Q Network Partial Observability
  • Graph Convolutional Network (GCN), Graph Neural Networks (Graph Nets), Geometric Deep Learning
  • Capsule Networks (CapNets)
  • Messaging & Routing
  • Pipelines
  • Federated
  • Processing Units - CPU, GPU, APU, TPU, VPU, FPGA, QPU
• Integrity Forensics
• Other Challenges in Artificial Intelligence

Development & Implementation

• Building Your Environment
• Pipelines
• Service Capabilities
• AI Marketplace & Toolkit/Model Interoperability

No Coding

• Automated Machine Learning (AML) - AutoML
• Neural Architecture Search (NAS) Algorithm
• Other codeless options, Code Generators, Drag n' Drop

Coding

• Javascript
• Python
• R Project
• Other Coding options

Libraries & Frameworks

• Libraries & Frameworks Overview

TensorFlow

• TensorBoard
• TensorFlow Playground
• TensorFlow.js Demos
• TensorFlow.js
• TensorFlow Lite
• TensorFlow Serving
• Related...
  • Keras.js
  • TFLearn
  • Swift

Tooling

• Model Search
• Model Monitoring
• Notebooks; Jupyter and R Markdown

Platforms: Machine Learning as a Service (MLaaS)

• Google Cloud Platform (GCP)
• Amazon AWS
• Microsoft Azure
• NVIDIA
• Kaggle
• Intel
• Apple

... and other leading organizations

• Allen Institute for Artificial Intelligence, or AI2
• OpenAI

If you get a 502 or 503 error please try the webpage again, as your message is visiting the island which the server is located, perhaps deciding to relax in the Sun before returning. Thank you.