Difference between revisions of "PRIMO.ai"
| Line 49: | Line 49: | ||
* [http://www.youtube.com/user/IntegrateBiz/playlists Intersection of Artificial Intelligence and Architecture | Raj Ramesh] | * [http://www.youtube.com/user/IntegrateBiz/playlists Intersection of Artificial Intelligence and Architecture | Raj Ramesh] | ||
| − | |||
| − | |||
| − | + | == Predict values == | |
| − | |||
| − | |||
| − | |||
* [[Linear Regression]] | * [[Linear Regression]] | ||
* [[Ridge Regression]] | * [[Ridge Regression]] | ||
| Line 69: | Line 64: | ||
* [[One-class Support Vector Machine (SVM)]] | * [[One-class Support Vector Machine (SVM)]] | ||
| − | + | ||
| − | * [[Perceptron (P)]] ...and Multi-layer Perceptron (MLP) | + | == Classification [[...predict categories]] == |
| − | + | * [[Supervised]] | |
| + | ** [[Naive Bayes]] | ||
| + | ** [[K-Nearest Neighbors (KNN)]] | ||
| + | ** [[Perceptron (P)]] ...and Multi-layer Perceptron (MLP) | ||
** [[Feed Forward Neural Network (FF or FFNN)]] | ** [[Feed Forward Neural Network (FF or FFNN)]] | ||
** [[Artificial Neural Network (ANN)]] | ** [[Artificial Neural Network (ANN)]] | ||
** [[Deep Neural Network (DNN)]] | ** [[Deep Neural Network (DNN)]] | ||
| − | * [[Kernel Approximation]] | + | ** [[Kernel Approximation]] |
| − | ** [[Support Vector Machine (SVM)]] | + | *** [[Support Vector Machine (SVM)]] |
| − | * [[Logistic Regression (LR)]] | + | ** [[Logistic Regression (LR)]] |
| − | * [[Tree-based...]] | + | ** [[Tree-based...]] |
| − | ** [[(Boosted) Decision Tree]] | + | *** [[(Boosted) Decision Tree]] |
| − | ** [[Random Forest (or) Random Decision Forest]] | + | *** [[Random Forest (or) Random Decision Forest]] |
| − | ** [[Decision Jungle]] | + | *** [[Decision Jungle]] |
| − | + | * [[Unsupervised]] | |
| − | * [[ | + | ** [[Radial Basis Function Network (RBFN)]] |
| + | |||
| + | == [[Recommendation]] == | ||
* [[Alternating Least Squares (ALS)]] | * [[Alternating Least Squares (ALS)]] | ||
* [[Matrix Factorization]] | * [[Matrix Factorization]] | ||
| − | == | + | == Categorical == |
| − | * [[ | + | * [[Supervised]] |
| − | * [[( | + | ** [[Apriori, Frequent Pattern (FP) Growth, Association Rules/Analysis]] |
| − | ** [[ | + | ** [[Markov Model (Chain, Discrete Time, Continuous Tme, Hidden)]] |
| − | + | * [[Unsupervised]] | |
| − | + | ** [[Autoencoder (AE) / Encoder-Decoder]] | |
| − | + | ** [[(Stacked) Denoising Autoencoder (DAE)]] | |
| − | + | ** [[Sparse Autoencoder (SAE)]] | |
| − | |||
| − | |||
| − | |||
| − | * [[ | ||
| − | |||
| − | |||
| − | *[[ | ||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | * | ||
| − | * [[ | ||
| − | |||
| − | + | == [[Clustering]] - Continuous - Dimensional Reduction == | |
* [[Singular Value Decomposition (SVD)]] | * [[Singular Value Decomposition (SVD)]] | ||
* [[Principal Component Analysis (PCA)]] | * [[Principal Component Analysis (PCA)]] | ||
| Line 126: | Line 108: | ||
* [[Variational Autoencoder (VAE)]] | * [[Variational Autoencoder (VAE)]] | ||
| − | + | === [[Hierarchical]] === | |
* [[Hierarchical Cluster Analysis (HCA)]] | * [[Hierarchical Cluster Analysis (HCA)]] | ||
* [[Hierarchical Clustering; Agglomerative (HAC) & Divisive (HDC)]] | * [[Hierarchical Clustering; Agglomerative (HAC) & Divisive (HDC)]] | ||
| Line 132: | Line 114: | ||
* [[Mixture Models; Gaussian]] | * [[Mixture Models; Gaussian]] | ||
| − | ==== | + | == Convolutional; Image & Object Recognition == |
| − | - | + | * [[(Deep) Convolutional Neural Network (DCNN/CNN)]] |
| − | * [[ | + | * [[(Deep) Residual Network (DRN) - ResNet]] |
| − | * [[( | + | ** [[ResNet-50]] |
| − | * [[ | + | |
| + | === [[Graph Convolutional Network (GCN)]] === | ||
| + | - includes social networks, sensor networks, the entire Internet, 3D Objects (point cloud) | ||
| + | * [[Point Cloud Convolutional Neural Network (CNN)]] | ||
| + | |||
| + | === Deconvolutional === | ||
| + | *[[Deconvolutional Neural Network (DN) / Inverse Graphics Network (IGN)]] | ||
| + | |||
| + | == Other == | ||
| + | * [[Hopfield Network (HN)]] | ||
| + | * [[Energy-based Model (EBN)]] | ||
| + | * [[Generative Query Network (GQN)]] | ||
| − | + | == Sequence / Time == | |
* [[Sequence to Sequence (Seq2Seq)]] | * [[Sequence to Sequence (Seq2Seq)]] | ||
* [[Neural Turing Machine]] | * [[Neural Turing Machine]] | ||
| Line 147: | Line 140: | ||
* [[(Tree) Recursive Neural (Tensor) Network (RNTN)]] | * [[(Tree) Recursive Neural (Tensor) Network (RNTN)]] | ||
| − | + | === Time === | |
* [[Temporal Difference (TD) Learning]] | * [[Temporal Difference (TD) Learning]] | ||
* Predict values | * Predict values | ||
| Line 153: | Line 146: | ||
** [[Time Series Forecasting - Deep Learning]] | ** [[Time Series Forecasting - Deep Learning]] | ||
| − | + | == Competitive == | |
| − | |||
* [[Generative Adversarial Network (GAN)]] | * [[Generative Adversarial Network (GAN)]] | ||
* [[Conditional Adversarial Architecture (CAA)]] | * [[Conditional Adversarial Architecture (CAA)]] | ||
| Line 160: | Line 152: | ||
| − | + | == [[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. | 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)]] | * [[Semi-Supervised Learning with Generative Adversarial Network (SSL-GAN)]] | ||
Revision as of 11:11, 8 January 2019
On Friday March 27, 2026 PRIMO.ai has 825 pages
Contents
- 1 Getting Started
- 2 Datasets & Information Analysis
- 3 Algorithms
- 3.1 Predict values
- 3.2 Classification ...predict categories
- 3.3 Recommendation
- 3.4 Categorical
- 3.5 Clustering - Continuous - Dimensional Reduction
- 3.6 Convolutional; Image & Object Recognition
- 3.7 Other
- 3.8 Sequence / Time
- 3.9 Competitive
- 3.10 Semi-Supervised
- 3.11 Natural Language Processing (NLP)
- 3.12 Reinforcement Learning (RL)
- 4 Techniques
- 5 Development & Implementation
- 6 Research
Getting Started
Overview
Background
AI Breakthroughs
AI Fun
- Google AI Experiments
- TensorFlow Playground
- TensorFlow.js Demos
- Do-it-yourself artificial intelligence | AIY
- Competitions
How to...
Forward Thinking
Datasets & Information Analysis
- Datasets
- Batch Norm(alization) & Standardization
- Data Preprocessing & Feature Exploration/Learning
- Hyperparameters
- Data Augmentation
- Visualization
- Master Data Management (MDM) / Feature Store / Data Lineage / Data Catalog
Algorithms
- About Algorithms & Neural Network Models
- Discriminative vs. Generative
- Intersection of Artificial Intelligence and Architecture | Raj Ramesh
Predict values
- Linear Regression
- Ridge Regression
- Bayesian Linear Regression
- Support Vector Regression (SVR)
- Ordinal Regression
- Poisson Regression
- Tree-based...
- Boosted Decision Tree Regression
- General Regression Neural Network (GRNN)
- One-class Support Vector Machine (SVM)
Classification ...predict categories
- Supervised
- Unsupervised
Recommendation
Categorical
Clustering - Continuous - Dimensional Reduction
- Singular Value Decomposition (SVD)
- Principal Component Analysis (PCA)
- K-Means
- 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)
Hierarchical
- Hierarchical Cluster Analysis (HCA)
- Hierarchical Clustering; Agglomerative (HAC) & Divisive (HDC)
- Hierarchical Temporal Memory (HTM) Time
- Mixture Models; Gaussian
Convolutional; Image & Object Recognition
Graph Convolutional Network (GCN)
- includes social networks, sensor networks, the entire Internet, 3D Objects (point cloud)
Deconvolutional
Other
Sequence / Time
- Sequence to Sequence (Seq2Seq)
- Neural Turing Machine
- Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and Recurrent Neural Network (RNN)
- (Tree) Recursive Neural (Tensor) Network (RNTN)
Time
- Temporal Difference (TD) Learning
- Predict values
Competitive
- Generative Adversarial Network (GAN)
- Conditional Adversarial Architecture (CAA)
- Kohonen Network (KN)/Self Organizing Maps (SOM)
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 Processing (NLP)
Challenges involve Speech recognition, (speech) translation, understanding (semantic parsing) complete sentences, understanding synonyms of matching words, sentiment analysis, and 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.
- 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)
- Hierarchical Reinforcement Learning (HRL)
Techniques
Foundation
- Math for Intelligence
- Arxiv Sanity Preserver to accelerate research
Methods
- Backpropagation
- Gradient Boosting Algorithms
- Overfitting Challenge
- Softmax
- Dimensional Reduction Algorithms; what influences an observed outcome
- Activation Functions
- Attention Mechanism/Model
- Multiclassifiers; Ensembles and Hybrids; Bagging, Boosting, and Stacking
- Object Detection; Faster R-CNN, YOLO, SSD
- Optimizers
- Few Shot Learning
- Multitask Learning
- Transfer Learning a model trained on one task is re-purposed on a second related task
- Repositories & Other Algorithms
Development & Implementation
Libraries & Frameworks
TensorFlow
- TensorFlow Overview & Tutorials
- TensorBoard
- TensorFlow.js
- TensorFlow Playground
- TensorFlow Lite
- TensorFlow Serving
- Related...
Tooling
Coding
Platforms: Machine Learning as a Service (MLaaS)
Google Cloud Platform (GCP) ...AI with TensorFlow
- Kubeflow ML workflows on Kubernetes
- Colaboratory - Jupyter notebooks
- Google Developers Codelabs
- Dopamine - reinforcement learning algorithms
- Google AI Experiments
- ML Engine
- Prediction API
- Cloud Vision API - drag & drop picture on webpage
- Grow with Google
- Learn from ML experts at Google
Amazon AWS
- AWS with TensorFlow
- DeepLens - deep learning enabled video camera
- AWS Internet of Things (IoT)
- AmazonML
- Deep Learning (DL) Amazon Machine Image (AMI) - DLAMI
- FloydHub - training and deploying your DL models
- On-Demand AWS Tech Talks
- AWS Training and Certification
Microsoft Azure
NVIDIA
Kaggle
Intel
Apple
Research
- Generative Modeling
- Automated Machine Learning (AML) - AutoML
- Explainable Artificial Intelligence (EAI)
- AI Marketplace & Toolkit/Model Interoperability
- Self Learning Artificial Intelligence - AutoML & World Models
- Connecting Brains
- Architectures
- Cybersecurity
- Integrity Forensics
- Other Challenges
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.
