added thesis

2022-10-21 07:08:34 +02:00
parent 55d8ebdf15
commit 48dd6045bb
12 changed files with 338 additions and 288 deletions
@@ -23,7 +23,7 @@ DATE: today
 * "Video  on Convolutional Neural Networks from MIT":"https://www.youtube.com/watch?v=iaSUYvmCekI&ab_channel=AlexanderAmini"
 * "Video on CNNs from Stanford":"https://www.youtube.com/watch?v=bNb2fEVKeEo&list=PLC1qU-LWwrF64f4QKQT-Vg5Wr4qEE1Zxk&index=6&ab_channel=StanfordUniversitySchoolofEngineering"
 !eblock
-
+m

 !bblock  And Lecture material on CNNs
 * "Lectures from IN5400 spring 2019":"https://www.uio.no/studier/emner/matnat/ifi/IN5400/v19/material/week5/in5400_2019_week5_convolutional_nerual_networks.pdf"
@@ -35,10 +35,10 @@ DATE: today

 !split
 ===== Using Automatic differentiation =====
-
+a
 In our discussions of ordinary differential equations 
 we will also study the usage of "Autograd":"https://www.youtube.com/watch?v=fRf4l5qaX1M&ab_channel=AlexSmola" in computing gradients for deep learning. For the documentation of Autograd and examples see the lectures slides from "week 39":"https://compphysics.github.io/MachineLearning/doc/pub/week39/html/week39.html" and the "Autograd documentation":"https://github.com/HIPS/autograd".
-
+t

 !split
 ===== Back propagation and automatic differentiation =====
@@ -62,6 +62,12 @@ and output layer to any given precision.
 "An Introduction to Neural Network Methods for Differential Equations":"https://www.springer.com/gp/book/9789401798150", by Yadav and Kumar.
 !eblock

+!bblock  Master thesis on applying deep learning to problems in mechanics
+"Using Deep Reinforcement Learning for Active Flow Control":"https://www.duo.uio.no/handle/10852/79212", by Marius Holm
+!eblock
+
+
+
 !bblock Thanks to Kristine Baluka Hein
 The lectures on differential equations were developed by Kristine Baluka Hein, now PhD student at IFI.
 A great thanks to Kristine.
@@ -2640,7 +2646,7 @@ We say we perform a filtering (convolution is the mathematical operation).

 The mathematics of CNNs is based on the mathematical operation of
 _convolution_.  In mathematics (in particular in functional analysis),
-convolution is represented by matheematical operation (integration,
+convolution is represented by mathematical operation (integration,
 summation etc) on two function in order to produce a third function
 that expresses how the shape of one gets modified by the other.
 Convolution has a plethora of applications in a variety of disciplines, spanning from statistics to signal processing, computer vision, solutions of differential equations,linear algebra, engineering,  and yes, machine learning.