Gustavo's webpages

❯

Folder: wiki

65 items under this folder.

Feb 05, 2025
Resoluções 2025
Dec 15, 2024
GARD
- folder
Dec 09, 2024
William Lane Craig
Nov 27, 2024
Batismo de crianças
- faith
Nov 26, 2024
Academic markdown with citation-reference manager
Nov 11, 2024
Gell-Mann Amnesia effect
Oct 11, 2024
Motives of Credibility
- faith
Oct 03, 2024
Hashcash is a proof of work algorithm
Sep 25, 2024
Lectio Divina
- catholicism
Sep 14, 2024
Assistolia Fetal
- aborto
Sep 14, 2024
O uso de cloreto de potássio para eutanásia em animais é inaceitável no Brasil.
Sep 13, 2024
A Markov process has the Markov Property
- math
Sep 13, 2024
Action Policy is a function that returns an action given an state
- cs
- econ
Sep 13, 2024
An AI Agent is an entity that can observe and act autonomously
- mlai
- cs
Sep 13, 2024
Avoid python loops when Pytorch functions are available
- mlai
Sep 13, 2024
Bellman Equation express a value function
Sep 13, 2024
Building a Linear Regression Model
Sep 13, 2024
Classification vs Regression models
- mlai
Sep 13, 2024
Convolutional Neural Networks
- mlai
- unaswered
Sep 13, 2024
DQN training doesn't rely on expected outputs
Sep 13, 2024
Data sets divide input data
- mlai
Sep 13, 2024
Deep Learning Jargon
- mlai
Sep 13, 2024
Deep Q Network (DQN) uses deep learning to do Q-learning
- mlai
- cs
Sep 13, 2024
Discount rates reflect timing and risk
- econ
Sep 13, 2024
Discounted Cash Flows is a way of valuing an asset
- econ
Sep 13, 2024
Epoch is a training cycle in model training
- mlai
Sep 13, 2024
Epsilon-greedy dictates the action of the agent during training
- newnote
- mlai
Sep 13, 2024
Fine-tuning
- mlai
Sep 13, 2024
Full text-search
- unaswered
Sep 13, 2024
Good code has good comments
- cleancode
Sep 13, 2024
Hash Collision
- cryptography
Sep 13, 2024
How can machines learn?
- mlai
Sep 13, 2024
How to sync Obsidian iOS with Google Drive
- incomplete
Sep 13, 2024
Information Hiding
- incomplete
Sep 13, 2024
Loss functions
- mlai
Sep 13, 2024
Markov Decision Process (MDP) is influenced by decisions and stochasticity
- math
- cs
Sep 13, 2024
Markov chain is a markov process
- math
Sep 13, 2024
Markovian text generation
- cs
Sep 13, 2024
Matrix multiplication
- incomplete
Sep 13, 2024
Moravec's Paradox
- mlai
Sep 13, 2024
Multi-writes may cause a system to transition to an invalid state
- improve
Sep 13, 2024
Mutations are not random
Sep 13, 2024
One dollar today is more valuable than one dollar tomorrow
- econ
Sep 13, 2024
Operations with tensors of different ranks use broadcasting
- mlai
Sep 13, 2024
Overfitting is a failure of model training
- mlai
Sep 13, 2024
Pre-trained model
- mlai
Sep 13, 2024
Pytorch tensor is a fast array for GPUs
- mlai
Sep 13, 2024
Q-function is a value function approximation
- mlai
- cs
Sep 13, 2024
Q-learning is the process of finding the best possible Q-function
- mlai
- cs
Sep 13, 2024
Quality metrics for estimators models
- unaswered
- math
Sep 13, 2024
ReLUs are used to introduce non-linearity in neural networks
- mlai
Sep 13, 2024
Regression Analysis
- math
Sep 13, 2024
Reinforcement Learning
- incomplete
- mlai
Sep 13, 2024
Replay Buffer register what is happening
- mlai
Sep 13, 2024
Residuals is the difference between the predicted value and actual value
- math
Sep 13, 2024
Sessions vs JWTs
- web
Sep 13, 2024
Sigmoids are used to ensure the value is between 0 and 1
- mlai
Sep 13, 2024
State Machines
- cs
Sep 13, 2024
State Transition Matrix maps states transitions according to actions.
- cs
Sep 13, 2024
Stochasticity
- unaswered
Sep 13, 2024
The head is the top of the neural network
- mlai
Sep 13, 2024
Train-Test Split
Sep 13, 2024
Transfer learning
- mlai
Sep 13, 2024
Weights and biases are the paremeters of a neural network
- mlai
Sep 13, 2024
Why the earlier layers don't require many changes in fine-tuning
- mlai
- unaswered

Made with ❤️ by Gustavo. Using Quartz v4.4.0 © 2025