From b30da1d29cf701ab497300124cd4ce2be1b6b060 Mon Sep 17 00:00:00 2001 From: andy Date: Thu, 1 Jun 2023 08:11:37 +0100 Subject: [PATCH] vault backup: 2023-06-01 08:11:37 Affected files: .obsidian/graph.json .obsidian/workspace.json Money/Assets/Derivative.md STEM/AI/Neural Networks/CNN/Examples.md STEM/AI/Neural Networks/Deep Learning.md STEM/AI/Neural Networks/MLP/Decision Boundary.md STEM/CS/Languages/dotNet.md STEM/Semiconductors/Equations.md Tattoo/Engineering.md --- AI/Neural Networks/CNN/Examples.md | 16 +++++++-------- AI/Neural Networks/Deep Learning.md | 22 ++++++++++----------- AI/Neural Networks/MLP/Decision Boundary.md | 7 +++---- CS/Languages/dotNet.md | 2 +- Semiconductors/Equations.md | 2 +- 5 files changed, 24 insertions(+), 25 deletions(-) diff --git a/AI/Neural Networks/CNN/Examples.md b/AI/Neural Networks/CNN/Examples.md index 6b78f4f..aff6269 100644 --- a/AI/Neural Networks/CNN/Examples.md +++ b/AI/Neural Networks/CNN/Examples.md @@ -1,8 +1,8 @@ # LeNet - 1990's -![[lenet-1989.png]] +![lenet-1989](../../../img/lenet-1989.png) - 1989 -![[lenet-1998.png]] +![lenet-1998](../../../img/lenet-1998.png) - 1998 # AlexNet @@ -11,7 +11,7 @@ - [[Activation Functions#ReLu|ReLu]] - Normalisation -![[alexnet.png]] +![alexnet](../../../img/alexnet.png) # VGG 2015 @@ -22,8 +22,8 @@ - Similar kernel size throughout - Gradual filter increase -![[vgg-spec.png]] -![[vgg-arch.png]] +![vgg-spec](../../../img/vgg-spec.png) +![vgg-arch](../../../img/vgg-arch.png) # GoogLeNet 2015 @@ -31,13 +31,13 @@ - [[Inception Layer]]s - Multiple [[Deep Learning#Loss Function|Loss]] Functions -![[googlenet.png]] +![googlenet](../../../img/googlenet.png) ## [[Inception Layer]] -![[googlenet-inception.png]] +![googlenet-inception](../../../img/googlenet-inception.png) ## Auxiliary [[Deep Learning#Loss Function|Loss]] Functions - Two other SoftMax blocks - Help train really deep network - Vanishing gradient problem -![[googlenet-auxilliary-loss.png]] \ No newline at end of file +![googlenet-auxilliary-loss](../../../img/googlenet-auxilliary-loss.png) \ No newline at end of file diff --git a/AI/Neural Networks/Deep Learning.md b/AI/Neural Networks/Deep Learning.md index 9857edd..98ceb8e 100644 --- a/AI/Neural Networks/Deep Learning.md +++ b/AI/Neural Networks/Deep Learning.md @@ -1,17 +1,17 @@ -![[deep-digit-classification.png]] +![deep-digit-classification](../../img/deep-digit-classification.png) # Loss Function Objective Function -- [[Back-Propagation]] +- [Back-Propagation](MLP/Back-Propagation.md) - Difference between predicted and target outputs -![[deep-loss-function.png]] +![deep-loss-function](../../img/deep-loss-function.png) - Test accuracy worse than train accuracy = overfitting - [[MLP|Dense]] = [[MLP|fully connected]] - Automates feature engineering -![[ml-dl.png]] +![ml-dl](../../img/ml-dl.png) These are the two essential characteristics of how deep learning learns from data: the incremental, layer-by-layer way in which increasingly complex representations are developed, and the fact that these intermediate incremental representations are learned jointly, each layer being updated to follow both the representational needs of the layer above and the needs of the layer below. Together, these two properties have made deep learning vastly more successful than previous approaches to machine learning. @@ -32,16 +32,16 @@ Predict Evaluate # Data Structure -- [[Tensor]] flow = channels last +- [Tensor](../../Maths/Tensor.md) flow = channels last - (samples, height, width, channels) - Vector data - - 2D [[tensor]]s of shape (samples, features) + - 2D [tensors](../../Maths/Tensor.md) of shape (samples, features) - Time series data or sequence data - - 3D [[tensor]]s of shape (samples, timesteps, features) + - 3D [tensors](../../Maths/Tensor.md) of shape (samples, timesteps, features) - Images - - 4D [[tensor]]s of shape (samples, height, width, channels) or (samples, channels, height, Width) + - 4D [tensors](../../Maths/Tensor.md) of shape (samples, height, width, channels) or (samples, channels, height, Width) - Video - - 5D [[tensor]]s of shape (samples, frames, height, width, channels) or (samples, frames, channels , height, width) + - 5D [tensors](../../Maths/Tensor.md) of shape (samples, frames, height, width, channels) or (samples, frames, channels , height, width) -![[photo-tensor.png]] -![[matrix-dot-product.png]] \ No newline at end of file +![photo-tensor](../../img/photo-tensor.png) +![matrix-dot-product](../../img/matrix-dot-product.png) \ No newline at end of file diff --git a/AI/Neural Networks/MLP/Decision Boundary.md b/AI/Neural Networks/MLP/Decision Boundary.md index d0e18f1..87c3c2a 100644 --- a/AI/Neural Networks/MLP/Decision Boundary.md +++ b/AI/Neural Networks/MLP/Decision Boundary.md @@ -1,4 +1,3 @@ -![[hidden-neuron-decision.png]] -![[mlp-xor.png]] - -![[mlp-xor-2.png]] \ No newline at end of file +![hidden-neuron-decision](../../../img/hidden-neuron-decision.png) +![mlp-xor](../../../img/mlp-xor.png) +![mlp-xor-2](../../../img/mlp-xor-2.png) \ No newline at end of file diff --git a/CS/Languages/dotNet.md b/CS/Languages/dotNet.md index 564d87a..ef5c02a 100644 --- a/CS/Languages/dotNet.md +++ b/CS/Languages/dotNet.md @@ -30,4 +30,4 @@ - Portable executable (PE) - DLL, EXE -![[cli-infrastructure.png]] \ No newline at end of file +![cli-infrastructure](../../img/cli-infrastructure.png) \ No newline at end of file diff --git a/Semiconductors/Equations.md b/Semiconductors/Equations.md index 7f81f16..b67fe2a 100644 --- a/Semiconductors/Equations.md +++ b/Semiconductors/Equations.md @@ -11,7 +11,7 @@ $$J=\sigma E$$ $$V_{bi} = \frac{kT}{q}ln(\frac{N_D N_A}{n_i^2})$$ - $V_{bi}$ = Built-in Potential -[[Doping]] +[Doping](Doping.md) $$J=nev$$ - $n$ = Charge Density - $e$ = Charge