notes

commit 5ae828e48b080ada03a7afd795f4dcd278a78001
parent 54ba1fcd1d143b14cd0cfd62f2e96825fbce003b
Author: AndrewLockVI <andrewlaack1@gmail.com>
Date:   Mon, 20 Jan 2025 09:48:21 -0600

Filled in dl notes

Diffstat:
A
definitions/Broadcasting.md
 | 
11
+++++++++++
M
definitions/DeepLearning.md
 | 
17
++++++++---------
A
definitions/L1Norm.md
 | 
11
+++++++++++
A
definitions/L2Norm.md
 | 
9
+++++++++
A
definitions/Norm.md
 | 
11
+++++++++++
A
definitions/Singular.md
 | 
11
+++++++++++

6 files changed, 61 insertions(+), 9 deletions(-)
diff --git a/definitions/Broadcasting.md b/definitions/Broadcasting.md
@@ -0,0 +1,11 @@
+# Broadcasting
+
+**Source:** Deep Learning
+
+**Chapter:** 2
+
+## Notes
+
+**Definition:** Broadcasting is the process of iteratively applying a lower dimensional operation on higher dimensional structures.
+
+An example of broadcasting is adding a vector to a matrix where each column in the matrix adds the corresponding coordinate in the vector to itself.
diff --git a/definitions/DeepLearning.md b/definitions/DeepLearning.md
@@ -22,12 +22,11 @@ Chapter 1
 
 Chapter 2
 
-- Tensor
-- Transpose
-- Broadcasting
-- Span
-- Singular
-- Norm
-- Lp Norm
-- L1 Norm
-- L2 Norm
+- [Tensor](Tensor.md)
+- [Transpose](Transpose.md)
+- [Broadcasting](Broadcasting.md)
+- [Span](Span.md)
+- [Singular](Singular.md)
+- [Norm](Norm.md)
+- [L1Norm](L1Norm.md)
+- [L2Norm](L2Norm.md)
diff --git a/definitions/L1Norm.md b/definitions/L1Norm.md
@@ -0,0 +1,11 @@
+# L1 Norm
+
+**Source:** Deep Learning
+
+**Chapter:** 2
+
+## Notes
+
+**Definition:** L1 norm is computed as described by [Norm](Norm.md) and represents the sum of all coordinates of a given vector.
+
+This is also referred to as the taxicab norm because if we think about the distances it would take to reach a given point by only going in a straight line, this number is the L1 norm.
diff --git a/definitions/L2Norm.md b/definitions/L2Norm.md
@@ -0,0 +1,9 @@
+# L2 Norm
+
+**Source:** Deep Learning
+
+**Chapter:** 2
+
+## Notes
+
+**Definition:** L2 norm is the standard euclidean distance.
diff --git a/definitions/Norm.md b/definitions/Norm.md
@@ -0,0 +1,11 @@
+# Norm
+
+**Source:** Deep Learning
+
+**Chapter:** 2
+
+## Notes
+
+**Definition:** Norm is a derived value which is defined as follows:
+
+||v_p|| = sum(|v_i|^p)^1/p where p > 0
diff --git a/definitions/Singular.md b/definitions/Singular.md
@@ -0,0 +1,11 @@
+# Singular
+
+**Source:** Deep Learning
+
+**Chapter:** 2
+
+## Notes
+
+**Definition:** For a matrix to be singular it must be a square matrix with a deteminant of zero.
+
+Given this definition, we also see this means the matrix must not be invertible.