Difference between revisions of "Neural Architecture"
m |
m |
||
| (One intermediate revision by the same user not shown) | |||
| Line 20: | Line 20: | ||
* [[Hierarchical Temporal Memory (HTM)]] | * [[Hierarchical Temporal Memory (HTM)]] | ||
* [[Codeless Options, Code Generators, Drag n' Drop]] | * [[Codeless Options, Code Generators, Drag n' Drop]] | ||
| − | * | + | * [[Artificial General Intelligence (AGI) to Singularity]] ... [[Inside Out - Curious Optimistic Reasoning| Curious Reasoning]] ... [[Emergence]] ... [[Moonshots]] ... [[Explainable / Interpretable AI|Explainable AI]] ... [[Algorithm Administration#Automated Learning|Automated Learning]] |
* [[Auto Keras]] | * [[Auto Keras]] | ||
* [[Symbiotic Intelligence]] ... [[Bio-inspired Computing]] ... [[Neuroscience]] ... [[Connecting Brains]] ... [[Nanobots#Brain Interface using AI and Nanobots|Nanobots]] ... [[Molecular Artificial Intelligence (AI)|Molecular]] ... [[Neuromorphic Computing|Neuromorphic]] ... [[Evolutionary Computation / Genetic Algorithms| Evolutionary/Genetic]] | * [[Symbiotic Intelligence]] ... [[Bio-inspired Computing]] ... [[Neuroscience]] ... [[Connecting Brains]] ... [[Nanobots#Brain Interface using AI and Nanobots|Nanobots]] ... [[Molecular Artificial Intelligence (AI)|Molecular]] ... [[Neuromorphic Computing|Neuromorphic]] ... [[Evolutionary Computation / Genetic Algorithms| Evolutionary/Genetic]] | ||
| Line 47: | Line 47: | ||
Various approaches to Neural Architecture Search (NAS) have designed networks that are on par or even outperform hand-designed architectures. Methods for NAS can be categorized according to the search space, search strategy and performance estimation strategy used: | Various approaches to Neural Architecture Search (NAS) have designed networks that are on par or even outperform hand-designed architectures. Methods for NAS can be categorized according to the search space, search strategy and performance estimation strategy used: | ||
| − | * The search space defines which type of [[Neural Network|artificial neural networks (ANN]] can be designed and optimized in principle. | + | * The search space defines which type of [[Neural Network|artificial neural networks (ANN}]] can be designed and optimized in principle. |
* The search strategy defines which strategy is used to find optimal [[Neural Network|ANN]]'s within the search space. | * The search strategy defines which strategy is used to find optimal [[Neural Network|ANN]]'s within the search space. | ||
* Obtaining the performance of an [[Neural Network|ANN]] is costly as this requires training the [[Neural Network|ANN]] first. Therefore, performance estimation strategies are used obtain less costly estimates of a model's performance. [http://en.wikipedia.org/wiki/Neural_architecture_search Neural Architecture Search | Wikipedia] | * Obtaining the performance of an [[Neural Network|ANN]] is costly as this requires training the [[Neural Network|ANN]] first. Therefore, performance estimation strategies are used obtain less costly estimates of a model's performance. [http://en.wikipedia.org/wiki/Neural_architecture_search Neural Architecture Search | Wikipedia] | ||
Latest revision as of 20:07, 8 September 2023
YouTube search... ...Google search
- Artificial Intelligence (AI) ... Machine Learning (ML) ... Deep Learning ... Neural Network ... Reinforcement ... Learning Techniques
- Hierarchical Temporal Memory (HTM)
- Codeless Options, Code Generators, Drag n' Drop
- Artificial General Intelligence (AGI) to Singularity ... Curious Reasoning ... Emergence ... Moonshots ... Explainable AI ... Automated Learning
- Auto Keras
- Symbiotic Intelligence ... Bio-inspired Computing ... Neuroscience ... Connecting Brains ... Nanobots ... Molecular ... Neuromorphic ... Evolutionary/Genetic
- Hyperparameters Optimization
- Model Search
- Google AutoML
- MIT’s AI can train neural networks faster than ever before | Christine Fisher - Engadget
Neural Architecture Search (NAS)
YouTube search... ...Google search
- Literature on Neural Architecture Search | AutoML.org
- Awesome NAS; a curated list
- Neural Architecture Search (NAS) with Reinforcement Learning | Wikipedia
- Neural Architecture Search (NAS) with Evolution | Wikipedia
- Multi-objective Neural architecture search | Wikipedia
- Neural Architecture Search for Deep Face Recognition | Ning Zhu
An alternative to manual design is “neural architecture search” (NAS), a series of machine learning techniques that can help discover optimal neural networks for a given problem. Neural architecture search is a big area of research and holds a lot of promise for future applications of deep learning. * Need to find the best AI model for your problem? Try neural architecture search | Ben Dickson - TDW NAS algorithms are efficient problem solvers ... What is neural architecture search (NAS)? | Ben Dickson - TechTalks
Various approaches to Neural Architecture Search (NAS) have designed networks that are on par or even outperform hand-designed architectures. Methods for NAS can be categorized according to the search space, search strategy and performance estimation strategy used:
- The search space defines which type of artificial neural networks (ANN} can be designed and optimized in principle.
- The search strategy defines which strategy is used to find optimal ANN's within the search space.
- Obtaining the performance of an ANN is costly as this requires training the ANN first. Therefore, performance estimation strategies are used obtain less costly estimates of a model's performance. Neural Architecture Search | Wikipedia
Differentiable Neural Computer (DNC)
Neural Operator
YouTube search... ...Google search
- Geology: Mining, Oil & Gas
- Neural Operator: Learning Maps Between Function Spaces | N. Kovachki, Z. Li, B. Liu, K. Azizzadenesheli, K. Bhattacharya, A. Stuart, Animashree (Anima) Anandkumar
- Neural Operator – Solving PDEs; Partial Differential Equations | Animashree (Anima) Anandkumar, Andrew Stuart, & Kaushik Bhattacharya]
A generalization of neural networks to learn operators, termed neural operators, that map between infinite dimensional function spaces. A universal approximator in the function space. the Fourier neural operator model has shown state-of-the-art performance with 1000x speedup in learning turbulent Navier-Stokes equation, as well as promising applications in weather forecast and CO2 migration, as shown in the figure below. Neural Operator Machine learning for scientific computing | Zongy Li
