Skip to main content
Ctrl+K

solAiKM

  • solai

AI24

  • links
  • Machine Learning
    • Labs
      • normalize or not to normalize
      • grid search pipe
      • scaler normalization
      • missing values handeling
      • PPS - Predictive Power Score
    • Intro
      • About ML
      • ML types
      • applications
      • hyperparams
      • pipeline
      • human intuition
    • General topics
      • Classification vs Regression
      • Complex Step Differentiation
      • feature processing
      • Tree Ensemble vs Random Forest
      • representation tricks
    • Scikit
      • about scikit
      • fetch_openml
      • SVC
      • knn
      • cross validation
      • classification_report
      • Decision function
      • fscoreSupport
      • PlotConfusionMatrix
      • roc curve
      • preprocessing
      • pipeline
      • DecisionTreeClassifier
      • CalibratedClassifierCV
      • check_estimator
      • logistics regression
      • classification metrics
      • Speeding up scikit-learn
    • Classification
      • Binary Classification
      • linear classifiers
        • Linear Classifier
        • ReParametrization
        • Linear Classifier Random
        • Linear Classifier MOONs
        • Linear Classifier breast
      • SVM - support vector machine
        • Support Vector Machines (SVM)
        • SVM Rand classification
        • SVM breast classification
      • k nearest neighbors
        • KNN
        • curse of dimensionality
        • KNN random circles
        • KNN brest
        • Curse lab
      • training
        • mnist multicalass example
        • K FOLD
        • Data Split
        • Training Process Comparison
        • resampling
      • multi-class
      • precision and recall
      • Balanced Accuracy
      • Roc
      • cost
      • classification labs
        • Performance Scores demo
        • MNIST KNN
        • MNIST SVM
        • Decision Functions Demos
        • Performance Scores
        • Calibrating Imbalanced
        • Understanding the AUC
        • TensorBoard
    • Feature Engineering
      • Normalizing and Standardizing
      • Non Separable Problem
      • technics list
      • Features Transform case1
      • Features Transform case2
      • Outline
      • Kernel Tricks
      • Kernel SVM
      • mnist example with kernel trick
      • fashion-mnist
      • AutoML
    • Statistical Classification
      • logistic regression
      • Demo Lab Logistic Regression
      • Cross Entropy
      • Mnist Logistic Regression
      • MAP Classifier
      • Naive Bayes Classifier
      • Naive Bayes Classifier
    • Decision Trees
      • Decision Trees
      • Circles Decision Tree Classifier
      • Heart Disease Tree Classifier
    • Linear Regression
      • Linear Regression: Model Imperfection and Steps to Implement Regression
      • Polynomial regression
      • Phase Estimation
      • Polynomial Fit
      • AI Program
      • Ridge Regression
      • R2 Score
      • Least Squares with \({L}^{1}\) / \({L}^{2}\) Regularization
      • Polynomial Fit with LASSO Regularization
      • outliers
      • huber
      • LS outiner
      • RANSAC
      • Polynomial Fit with RANSAC
      • Weighted Least Squares
      • Non-Linear Least Squares (NLLS)
      • ElasticNet
    • Non parametric regression
      • kernel regression
      • Multivariate Kernel Regression
      • Kernel Regression
      • boston house Kernel Regression
      • Polynomial Regression
      • Polynomial Regression
      • Spline Interpolation
      • Regression Tree
      • Regression - Decision Tree
    • Ensemble Methods
      • Bias Variance Tradeoff
      • Bagging
      • Out-of-Bag Error (OOB)
      • Variance and Bias Trade-off
      • Random Forest
      • feature importances
      • MDI
      • permutation importance
      • Random Forests
      • Gradient boosting
      • Gradient Boosting
      • ada boost
      • Adaptive Boosting
      • LightGBM
      • XGBoost
    • Clustering
      • clustering
      • K-Means
      • K-Means
      • color space quantization
      • K-Means super pixcel
      • GMM
      • Gaussian Mixture Models (GMM)
      • Hierarchical clustering
      • Hierarchical Clustering
      • Density
      • DBSCAN Demo
      • HDBSCAN
      • HDBSCAN Demo
    • Dimensionality Reduction
      • pca
      • Rotation
      • Eigen Decomposition
      • Full PCA
      • oose
      • svd (pca)
      • Gene PCA DEMO LAB
      • PCA DEMO FACES
      • PCA Brest Cancer
      • non Linear PCA
      • Kernel PCA
      • Dual PCA
      • Dimensionality Reduction - Kernel PCA
      • MDS
      • MultiDimensional Scaling (MDS)
    • Manifold Learning
      • isoMap
      • Manifold Learning - IsoMap
      • Spectral Clustering
      • TSNE
      • t-SNE Demo
      • Entropy
      • Umap
      • parametric Embedding
      • umap demo
      • manifold concepts demo
      • Manifold Learning - multi model compare
    • Anomaly detection
      • zscore
      • Mahalanobis
      • Time Series
      • Local Outlier Factor
      • Local Outlier Factor
      • LOF Exercise
      • Isolation forest
      • Anomaly Detection - Isolation Forest
      • Isolation Forest - Exercise
    • text Analysis
      • text opts
  • AI Computer Vision
    • Labs
    • Convolution in Deep Learning
      • Fully Connected Drawbacks
      • CNN for Frequency Estimation Problem
      • Convolution for Frequency Estimation
      • 2D Convolution
      • Layers in Convolutional Neural Networks
      • Pooling in Convolutional Neural Networks
      • Batch Normalization
      • demo batch norm
      • Common Filters for 2D Convolution
      • Common Filters for 2D Convolution
      • Receptive Field (RF)
      • Calc RF
      • Encode-Decode Networks
      • skip connections
      • cifar10-2d-convolution
      • Image Classification Fashion MNIST
      • studentTeacherDemo
    • pytorch for CV
      • pytorch layers
      • custom nn
      • micro macro
      • TorchVision
      • torchvision.transforms
    • Augmentation
      • Image Augmentation
      • Cut Effects
      • Image Augmentation
      • Smoothing
      • Label Smoothing
      • Regularized Training
    • compare
      • darknet53
      • AlexNet
      • vgg
      • googleNet
      • Inception Modules
      • resnet
      • ResNet Model
      • yolo
      • minirocket
      • lab simple minirocket demo
    • Pre-Defined Models
      • pytorch Inference
      • sota - state-of-the-art
      • zoo(s)
      • Pre Trained Computer Vision Models
    • Transfer Learning
      • compare methods
      • Fine-Tuning
      • Freeze Layers
      • Transfer Learning of resnet
      • Transfer overfit
      • lab reduce demo
      • transformers
      • lab transform basic
      • adaptation
    • visualize and debug
    • Object Location
      • pre-trained model for object localization
      • Localization
      • Object Localization
      • Detection
      • Transforms v2: End-to-end object detection/segmentation example
      • Common Object Detector Architecture
      • Non Maximum Suppression (NMS)
      • Mean Average Precision (mAP)
      • WorkShop - Object Detection with Yolov8
      • label example
      • yoloWRKSHP box formats
    • segmentation workshop
      • intro
      • data
      • models
      • UNET
      • the task
  • Repository
  • Open issue
  • .md

links

Contents

  • frameworks
    • Deep explanations
    • concepts
    • math
    • visualization
    • blogs
    • books
    • articles
    • feature tools
    • deep
    • Torch
  • training
    • cv
      • math
  • gpu rental
  • no code ai
  • augmentations
  • projects:

links#

frameworks#

  • https://openml.org/ open platform for sharing datasets, algorithms, and experiments

  • https://www.kaggle.com/ - Kaggle

Deep explanations#

  • https://theaisummer.com/ - read about deep learning

  • https://explained.ai/ - Deep explanations

  • https://udlbook.github.io/udlbook/ - Understanding Deep Learning

  • https://www.bishopbook.com/ - comprehensive introduction to the central ideas

  • https://www.deeplearningbook.org/ - mit Press book repo

  • https://d2l.ai/chapter_convolutional-modern/index.html - architectures

concepts#

  • https://nhigham.com/index-of-what-is-articles/ - What is …?

math#

  • https://www.matrixcalculus.org/ - derivative calculator

visualization#

  • dair-ai/ml-visuals - presentation figures

  • https://www.data-to-viz.com/ - visualization data

  • lilipads/gradient_descent_viz - gradient descent visualization

  • ashishpatel26/Tools-to-Design-or-Visualize-Architecture-of-Neural-Network - tools repo

  • https://alexlenail.me/NN-SVG/ - NN-architecture schematics

  • LucaBonfiglioli/nnviz - visualize neural networks

  • johnmarktaylor91/torchlens - TorchLens visualization

  • lutzroeder/Netron - viewer for neural network

  • https://arxiv.org/abs/1311.2901 - Feature Visualization

blogs#

  • https://dm13450.github.io/blog/ - Markwick blog

  • https://lilianweng.github.io/ - Lil’Log blog

  • https://lernapparat.de/statistics-deep-learning-nonparametric

  • filter increase

books#

  • gimac/gninrael-enihcam - collection repo

  • christianversloot/machine-learning-articles - articles repo

articles#

  • https://scribe.rip/4e79bd3b1b54 - memory access perspective on GPUs

  • https://scribe.rip/841dba49df5e - Explanation of the Dimensions in CNN

  • https://scribe.rip/ee40425aea1f - resnext

  • https://scribe.rip/92941c5bfb95 - EfficientNet

  • https://scribe.rip/36d53571365e - yolo

  • https://www.jeremyjordan.me/semantic-segmentation/ - semantic segmentation

  • https://scribe.rip/3f330efe697b - Average Precision

feature tools#

  • alteryx/featuretools

  • martineastwood/featuristic

  • Yimeng-Zhang/feature-engineering-and-feature-selection

  • aikho/awesome-feature-engineering

  • featuretools

  • feature_engine

  • Python-Feature-Engineering-Cookbook

deep#

  • KindXiaoming/pykan - Kolmogorov-Arnold (KAN) Networks

Torch#

  • davidstutz/torch-examples - Torch Examples

  • https://torchdrift.org/ - drift detection for PyTorch

  • Classification implemented using PyTorch

  • qubvel-org/segmentation_models.pytorch - segmentation models in PyTorch

  • pytorch/captum - model interpretability

#

  • https://optuna.org/ - A hyperparameter optimization framework

  • https://www.nltk.org/ - embedding

  • ddbourgin/numpy-ml - collection of machine learning algorithms implemented exclusively in NumPy

training#

  • https://www.deeplearning.ai/short-courses/ - short courses

  • uni-tuebingen course on Deep Learning

  • https://d2l.ai/ - Dive into Deep Learning

cv#

  • ML-4360 Faculty of Science Autonomous Vision

  • Deep Learning on Computational Accelerators - CS236781

  • https://lilianweng.github.io/posts/2017-10-29-object-recognition-part-1/

  • https://lilianweng.github.io/posts/2017-12-15-object-recognition-part-2/

  • https://lilianweng.github.io/posts/2017-12-31-object-recognition-part-3/

  • https://lilianweng.github.io/posts/2018-12-27-object-recognition-part-4/

math#

  • mitmath/matrixcalc - MIT Matrix Calculus for Machine Learning 18.S096

  • https://mml-book.github.io/ - (mmlBook) Mathematics for Machine Learning

  • https://mixtape.scunning.com/ - Mixtape: Explaining the Mathematics of Machine Learning

  • srush/Tensor-Puzzles - Tensor Puzzles

gpu rental#

  • https://vast.ai

no code ai#

  • https://www.ultralytics.com/

    • ultralytics

    • ultralytics/ultralytics

augmentations#

  • https://albumentations.ai/

projects:#

  • large scale obss/sahi

  • facebookresearch/detectron2

  • ultralytics/ultralytics

  • Lightning-Universe/lightning-bolts

previous

solai

next

Machine Learning

Contents
  • frameworks
    • Deep explanations
    • concepts
    • math
    • visualization
    • blogs
    • books
    • articles
    • feature tools
    • deep
    • Torch
  • training
    • cv
      • math
  • gpu rental
  • no code ai
  • augmentations
  • projects:

By 0xsol

© Copyright 2023.