Andy Pack
abbd7bba68
Affected files: .obsidian/community-plugins.json .obsidian/graph.json .obsidian/plugins/calendar/data.json .obsidian/plugins/calendar/main.js .obsidian/plugins/calendar/manifest.json .obsidian/plugins/dataview/main.js .obsidian/plugins/dataview/manifest.json .obsidian/plugins/dataview/styles.css .obsidian/workspace.json Events/Cardiff.md Events/November 27th Week.md Events/🪣🪣🪣.md Food/From Aldi.md Food/Meal Plans/Meals - 2023-06-18.md Food/Meal Plans/Meals - 2023-06-24.md Food/Meal Plans/Meals - 2023-07-30.md Food/Meal Plans/Meals - 2023-08-06.md Food/Meal Plans/Meals - 2023-08-13.md Food/Meal Plans/Meals - 2023-08-20.md Food/Meal Plans/Meals - 2023-08-27.md Food/Meal Plans/Meals - 2023-09-03.md Food/Meal Plans/Meals - 2023-09-10.md Food/Meal Plans/Meals - 2023-09-17.md Food/Meal Plans/Meals - 2023-09-25.md Food/Meal Plans/Meals - 2023-10-02.md Food/Meal Plans/Meals - 2023-10-14.md Food/Meal Plans/Meals - 2023-10-22.md Food/Meal Plans/Meals - 2023-10-30.md Food/Meal Plans/Meals - 2023-11-05.md Food/Meal Plans/Meals - 2023-11-14.md Food/Meal Plans/Meals - 2023-11-20.md Food/Meal Plans/Meals - 2023-12-03.md Food/Meal Plans/Meals - 2023-12-11.md Food/Meal Plans/Meals - 2023-12-16.md Food/Meals.md Food/Sauces.md Lab/DNS.md Lab/Deleted Packages.md Lab/Domains.md Lab/Ebook Laundering.md Lab/Home.md Lab/Linux/Alpine.md Lab/Linux/KDE.md Lab/Photo Migration.md Lab/VPN Servers.md Languages/Arabic.md Languages/Spanish/Spanish.md Languages/Spanish/Tenses.md Languages/Spanish/Verbs.md Money/Me/Accounts.md Money/Me/Car.md Money/Me/Home.md Money/Me/Income.md Money/Me/Monthly/23-04.md Money/Me/Monthly/23-05.md Money/Me/Monthly/23-06.md Money/Me/Monthly/23-07.md Money/Me/Monthly/23-08.md Money/Me/Monthly/23-09.md Money/Me/Monthly/23-10.md Money/Me/Monthly/23-11.md Money/Me/Monthly/23-12.md Money/Me/Subs.md STEM/AI/Classification/Classification.md STEM/AI/Classification/Decision Trees.md STEM/AI/Classification/Gradient Boosting Machine.md STEM/AI/Classification/Logistic Regression.md STEM/AI/Classification/Random Forest.md STEM/AI/Classification/Supervised/SVM.md STEM/AI/Classification/Supervised/Supervised.md STEM/AI/Ethics.md STEM/AI/Kalman Filter.md STEM/AI/Learning.md STEM/AI/Literature.md STEM/AI/Neural Networks/Activation Functions.md STEM/AI/Neural Networks/Architectures.md STEM/AI/Neural Networks/CNN/CNN.md STEM/AI/Neural Networks/CNN/Convolutional Layer.md STEM/AI/Neural Networks/CNN/Examples.md STEM/AI/Neural Networks/CNN/FCN/FCN.md STEM/AI/Neural Networks/CNN/FCN/FlowNet.md STEM/AI/Neural Networks/CNN/FCN/Highway Networks.md STEM/AI/Neural Networks/CNN/FCN/ResNet.md STEM/AI/Neural Networks/CNN/FCN/Skip Connections.md STEM/AI/Neural Networks/CNN/FCN/Super-Resolution.md STEM/AI/Neural Networks/CNN/GAN/CycleGAN.md STEM/AI/Neural Networks/CNN/GAN/DC-GAN.md STEM/AI/Neural Networks/CNN/GAN/GAN.md STEM/AI/Neural Networks/CNN/GAN/StackGAN.md STEM/AI/Neural Networks/CNN/GAN/cGAN.md STEM/AI/Neural Networks/CNN/Inception Layer.md STEM/AI/Neural Networks/CNN/Interpretation.md STEM/AI/Neural Networks/CNN/Max Pooling.md STEM/AI/Neural Networks/CNN/Normalisation.md STEM/AI/Neural Networks/CNN/UpConv.md STEM/AI/Neural Networks/CV/Data Manipulations.md STEM/AI/Neural Networks/CV/Datasets.md STEM/AI/Neural Networks/CV/Filters.md STEM/AI/Neural Networks/CV/Layer Structure.md STEM/AI/Neural Networks/CV/Visual Search/Visual Search.md STEM/AI/Neural Networks/Deep Learning.md STEM/AI/Neural Networks/Learning/Boltzmann.md STEM/AI/Neural Networks/Learning/Competitive Learning.md STEM/AI/Neural Networks/Learning/Credit-Assignment Problem.md STEM/AI/Neural Networks/Learning/Hebbian.md STEM/AI/Neural Networks/Learning/Learning.md STEM/AI/Neural Networks/Learning/Tasks.md STEM/AI/Neural Networks/MLP/Back-Propagation.md STEM/AI/Neural Networks/MLP/Decision Boundary.md STEM/AI/Neural Networks/MLP/MLP.md STEM/AI/Neural Networks/Neural Networks.md STEM/AI/Neural Networks/Properties+Capabilities.md STEM/AI/Neural Networks/RNN/Autoencoder.md STEM/AI/Neural Networks/RNN/Deep Image Prior.md STEM/AI/Neural Networks/RNN/LSTM.md STEM/AI/Neural Networks/RNN/MoCo.md STEM/AI/Neural Networks/RNN/RNN.md STEM/AI/Neural Networks/RNN/Representation Learning.md STEM/AI/Neural Networks/RNN/SimCLR.md STEM/AI/Neural Networks/RNN/VQA.md STEM/AI/Neural Networks/SLP/Least Mean Square.md STEM/AI/Neural Networks/SLP/Perceptron Convergence.md STEM/AI/Neural Networks/SLP/SLP.md STEM/AI/Neural Networks/Training.md STEM/AI/Neural Networks/Transformers/Attention.md STEM/AI/Neural Networks/Transformers/LLM.md STEM/AI/Neural Networks/Transformers/Transformers.md STEM/AI/Neural Networks/Weight Init.md STEM/AI/Pattern Matching/Dynamic Time Warping.md STEM/AI/Pattern Matching/Markov/Markov.md STEM/AI/Pattern Matching/Pattern Matching.md STEM/AI/Problem Solving.md STEM/AI/Properties.md STEM/AI/Searching/Informed.md STEM/AI/Searching/Searching.md STEM/AI/Searching/Uninformed.md STEM/CS/ABI.md STEM/CS/Calling Conventions.md STEM/CS/ISA.md STEM/CS/Languages/Assembly.md STEM/CS/Languages/Javascript.md STEM/CS/Languages/Python.md STEM/CS/Languages/Rust.md STEM/CS/Quantum.md STEM/CS/Resources.md STEM/IOT/Networking/Networking.md STEM/Light.md STEM/Quantum/Confinement.md STEM/Quantum/Orbitals.md STEM/Quantum/Schrödinger.md STEM/Quantum/Standard Model.md STEM/Quantum/Wave Function.md STEM/Speech/Linguistics/Consonants.md STEM/Speech/Linguistics/Language Structure.md STEM/Speech/Linguistics/Linguistics.md STEM/Speech/Linguistics/Terms.md STEM/Speech/Linguistics/Vowels.md STEM/Speech/Literature.md STEM/Speech/NLP/NLP.md STEM/Speech/NLP/Recognition.md STEM/Speech/Speech Processing/Applications.md Work/Possible Tasks.md Work/Tech.md
102 lines
3.2 KiB
Markdown
102 lines
3.2 KiB
Markdown
---
|
|
tags:
|
|
- ai
|
|
---
|
|
# Linearity
|
|
- Neurons can be linear or non-linear
|
|
- Network of non-linear neurons is non-linear
|
|
- Non-linearity is distributed
|
|
- Helpful if target signals are generated non-linearly
|
|
|
|
# Input-Output Mapping
|
|
- Map input signal to desired response
|
|
- [Supervised](../Learning.md#Supervised) learning
|
|
- Similar to non-parametric statistical inference
|
|
- Non-parametric as in no prior assumptions
|
|
- No probabilistic model
|
|
|
|
# Adaptivity
|
|
- Synaptic weights
|
|
- Can be easily retrained
|
|
- Stationary environment
|
|
- Essential statistics can be learned
|
|
- Model can then be frozen
|
|
- Non-stationary environments
|
|
- Can change weights in real-time
|
|
- In general, more adaptive = more robust
|
|
- Not always though
|
|
- Short time-constant system may be thrown by short-time spurious disturbances
|
|
- Stability-plasticity dilemma
|
|
- Not equipped to track statistical variations
|
|
- Adaptive system
|
|
- Linear adaptive filter
|
|
- Linear combiner
|
|
- Single neuron operating in linear mode
|
|
- Mature applications
|
|
- Nonlinear adaptive filters
|
|
- Less mature
|
|
- Environments typically considered pseudo-stationary
|
|
- Speech stationary over short windows
|
|
- Retrain network at regular intervals to account for fluctuations
|
|
- E.g. stock market
|
|
- Train network on short time window
|
|
- Add new data and pop old
|
|
- Slide window
|
|
- Retrain network
|
|
|
|
# Evidential Response
|
|
- Decisions are made with evidence not just declared
|
|
- Confidence value
|
|
|
|
# Contextual Information
|
|
- [Knowledge](Neural%20Networks.md#Knowledge) represented by structure and activation weight
|
|
- Any neuron can be affected by global activity
|
|
- Contextual information handled naturally
|
|
|
|
# Fault Tolerance
|
|
- Hardware implementations
|
|
- Performance degrades gracefully with adverse conditions
|
|
- If some of it breaks, it won't cause the whole thing to break
|
|
- Like a real brain
|
|
|
|
# VLSI Implementability
|
|
- Very large-scale integration
|
|
- Chips with millions of transistors (MOS)
|
|
- E.g. microprocessor, memory chips
|
|
- Massively parallel nature
|
|
- Well suited for VLSI
|
|
|
|
# Uniformity in Analysis
|
|
- Are domain agnostic in application
|
|
- Analysis methods are the same
|
|
- Can share theories, learning algorithms
|
|
|
|
# Neurobiological Analogy
|
|
- Design analogous to brain
|
|
- Already a demonstrable fault-tolerant, powerful, fast, parallel processor
|
|
|
|
- To slight changes
|
|
- Rotation of target in images
|
|
- Doppler shift in radar
|
|
- Network needs to be invariant to these transformations
|
|
|
|
# Invariance
|
|
1. Invariance by Structure
|
|
- Synaptic connections created so that transformed input produces same output
|
|
- Set same weight for neurons of some geometric relationship to image
|
|
- Same distance from centre e.g.
|
|
- Number of connections becomes prohibitively large
|
|
2. Invariance by Training
|
|
- Train on different views/transformations
|
|
- Take advantage of inherent pattern classification abilities
|
|
- Training for invariance for one object is not necessarily going to train other classes for invariance
|
|
- Extra load on network to do more training
|
|
- Exacerbated with high dimensionality
|
|
3. Invariant Feature Space
|
|
- Extract invariant features
|
|
- Use network as classifier
|
|
- Relieves burden on network to achieve invariance
|
|
- Complicated decision boundaries
|
|
- Number of features applied to network reduced
|
|
- Invariance ensured
|
|
- Required prior knowledge |