Category: LectureNotes
-
Dynamic Method Binding in Java
Why do we need dynamic method binding? Can we simply bind any method statically at compile time in Java? No! Let us see this example: The interesting part is that we don’t know the exact type of a variable in the program in run time. For example, check this program: But we can bind private/static/final…
-
Nvidia Driver – Cuda Mismatch
When I tried nvidia-smi, I got this error: As message indicates this is a version mismatch. I think this happened because of some automatic upgrade. Let us check the versions: The solution was to reinstall the CUDA toolkit from here: https://developer.nvidia.com/cuda-downloads
-
Kernel Trick Example
I’d like to demonstrate the kernel trick using a simple example here. The equations are taken from [1]. My motivation is to look from a more practical perspective. Inputs and Outputs Of course we have X as input and y as output. But I want to talk about inputs to the prediction equation to solve…
-
Precision vs. Recall
This is pretty explanatory. Here are some remarks on the meanings: Predictions specify whether the output is positive or negative Match between prediction and actual condition specify if the output is true or false Precision Precision is the measure of how we are successfully classifying the positives. More clearly, how much of the positive outputs…
-
Markov Decision Processes
We start with a basic formula, expected value. It is the expected value when you follow some transition function with some start state . Eq. 1: Note that the initial state is included in the reward function . Bellman TheoremA policy is optimal if and only if it is greedy with respect to its induced…
-
Word2Vec
It is a mapping of words to the vector space. Words will be represented as vectors to be used in machine learning domain. We can utilize this transformation and treat the words as mathematical objects to extract the required information. Granted we have the embeddings, we can do operations easily. Now it comes how to…
-
Static Games Intro – Notes
Definitions 1. Pure Nash Equilibrium It is when there is a state in which no player can make better profit by changing their action guaranteed no one else will change unreasonably their choice (other players are logical players) 2. Mixed Nash Equilibrium It is when you don’t know the opponents movement, or it is a…
-
Gaussian Process
What is a Gaussian Process?A GP is simply a multivariate Gauss distribution. The idea is very simple; we have a multivariate Gauss distribution which includes both previous measurements(or train set) and targets(test set). Either previous measurement or target, I will call them dimensions. They are some dimensions in the Gaussian Process. Since the multivariate Guassian…
-
Bayesian Deep Learning
Definitions Epistemic uncertainty:Uncertainty due to model itself, the model doesn’t represent the data completely because we have lack of information (obviously we have a finite set of data).Aleatoric uncertainty:Uncertainty inside the data itself. I think of it as measurement error in sensors.Heteroscedastic noise:The noise is not independent of the input features. For example, in Hadron…
-
Markov Chain Monte Carlo Methods
Some notes for myself… Just points to remember, I skip the overview and note the details that makes me grasp the concepts, usually why questions. Notice they are mostly my understanding from the lectures, and not intended to be a reference; I just type my understanding for future reference for myself. What is ergodicity in…