Machine Learning notes
40 notes by 28 users
This Machine Learning notes page gathers user-made notes on classification, regression, clustering and dimensionality reduction. It is for university students reviewing these topics and teachers choosing material for teaching. There are over 30 notes, contributed by more than 20 users. Pick a note to start exploring.
Select topic
- Types of Learning26
- Machine Learning Workflow and Deployment13
- Data Preparation7
- Feature Engineering and Dimensionality Reduction12
- Model Training and Optimization6
- Model Evaluation and Generalization14
- Regression25
- Classification8
- Decision Trees and Ensemble Learning11
- Support Vector Machines and Kernel Methods5
- Bayesian and Probabilistic Models13
- Clustering18
- Neural Networks and Deep Learning5
- Association Rules and Recommender Systems5
- Machine Learning Applications10
Notes
-
Principal Component Analysis Why learn PCA? The advantage of using PCA is: If you want to visualize the high dimensional data, then our pair plot, scatter plot all of them will not work. So, we always convert the data into 2 or 3 dimensions and t...
-
Dimensionality reduction and Visualization: What is Dimensionality reduction? We realize that we can visualize data in 2-D or 3-D using a simple scatter plot and for 4-D,5-D and even 6-D, we use pair plot to sense how data is. Note: If we have to visualize our ...
-
Bayesian networks - created from Mind Map
-
Untitled Ensemble Learning : There are two major benefits of Ensemble models: Better prediction More stable model Ensemble is the art of combining diverse set of learners (individual models) together to improvise on the stabil...
-
Clustering & Dimensionality Reduction Clustering Unsupervised Learning We don't have actual labels We may have groups, but nothing is defined and there are no correct answers Why use unsupervised Learning? Find similar data groups (clusters) Find outliers...
-
Edx- Course intro- 1) identify the sequence pattern. 2) make prediction about the next based on previous computers are good at doing calculations. So our job is to define a way for computer to do calculation in correct way....
-
introduction XGBoost: A Scalable Tree Boosting System supports both regression and classification predictive modeling problems (eXtreme Gradient Boosting) Gradient boosting : Idea : fitting a new model...
-
5 -2. Build model pipelines(5. Model Training) 2.1 - Preprocessing Sometimes we'll want to preprocess the training data even more before feeding it into our algorithms. For example, we may want to... Transform or scale our features. Perform automatic fea...
-
week 3
-
Naive Bayes
-
Machine Learning Types of Machine Learning Unsupervised ML Only inputs are provided, and the machine groups the data of its own. Eg: grouping news article of same type, grouping customers into different market segments. Grouping can b...
-
week 8
-
Overfitting - Underfitting - Regularization Low loss on validation set = better model. Overfitting : it's when the accuracy is high on the training set (which is often the case), but it does not generalize well on unseen data (the model doesn't perform we...
-
Machine Learning with Spark Supervised and Unsupervised Machine Learning Algorithms Summary: About the classification and regression supervised learning problems. About the clustering and association unsupervised learning problems. Example algor...
-
week 9 what is anamoly detection? take an example of aircraft engine; you have collected test data normal engines for heat and vibration levels; now for a new engine : (test) : how do you say that the engine will funct...
-
Common ML problems Three types of learning: Supervised learning: Model is provided with data (features) for specific labels. The model will then be able to make predictions by linking unseen data to labels. Unsupervised learning: Model ...
-
Supervised Learning Regression Analysis : Terminologies : 1. Target Variable - what we need to get also called Dependent variable 2. Independent Variables : this are the factors affecting the target variables also...
-
Untitled Linear Regression Our goal in linear regression is to predict a target value yy starting from a vector of input values x∈Rnx∈ℜn. For example, we might want to make predictions about the price of ...
-
week10 stochastic gradient descent : for dealing with large datasets - where batch gradient descent will be slower; because batch uses all 'm' examples in each iteration; randomly shuffle dataset then use below algorithm : u...
-
multivariate regression single variate regression: h-theta = theta-0 + theta-1 * x multi-variate: h-theta = theta-0 + theta-1 * x1 + theta-2 * x2 + theta-3*x3 +.....theta-n * xn alternately: h-theta = theta-0 * x-0 + theta-1 * x1 + the...
-
PCA - created from Mind Map Step 1: Covariance /Covariance Matrix of the dataset Motivation for PCA Step 0: Standarize dataset of dim(d)
-
Interview T-SNE - t-SNE differs from PCA by preserving only small pairwise distances or local similarities whereas PCA is concerned with preserving large pairwise distances to maximize variance PCA - PCA is a linear d...
-
Machine Learning Types by Task Classifications Clustering Predictions
-
Machine learning: Supervision Machine Learning: Supervision Machine learning algorithms can be broadly classified in terms of the amount of human supervision they require. The categories are Supervised Unsupervised Semisupervised lear...
-
polynomial regression
-
Hyper paramter What is the Difference Between a Parameter and a Hyperparameter? What is the Model Parameter? A model parameter is a configuration variable that is internal to the model and whose value can be estimated from data. The...
-
gradient descent :why is gradient descent needed? to find the minimum of a function...as in the cost function J(theta0, theta1) how does it work? start with theta0 and theta1 compute J(theta0, theta1) modify theta0 , theta1 to ...
-
week 7 support vector machine: variant of the logistic regression : minimize the cost of the logistic regression with a minor variation what is cost of logistic regression model? A + Lambda*B minimize it and identify the the...
-
Lecture1 notes If we want to penalise the formula why to use the absolute value rather than the square? L1 constraint is another name for the Lasso, while l2 might describe the ridge regression Ridge is lik...
-
Machine Learning - created from Mind Map Supervised Learning Vapnik-Chervonenkis (VC) Dimension Classification
-
Cost Function
-
Untitled Steps in Regression analytics Understanding the statement of the problem and analyse the Dependent and independent variables ( Dependent variable is continues in nature generally it is ...
-
week 11
-
English Sentence Hi folks, last time I wrote about Classification and Regression, by now I expect you to be able to differentiate regression and classification problem. Today we are going to define a regression problem and apply ...
-
Untitled Topic Modelling It is text data mining and statistical machine learning which consist of: Clustering words into “topics”. Clustering documents into “mixtures of topics”. More specifically: A Bayesian inference model t...
-
Machine Learning - created from Mind Map Definition Algorithm Supervised Learning監督學習： 從有結果的數據中訓練，從而獲得數據的結果的算法。
-
Machine Learning
-
Machine Learning Regression:- Predict Continous value output (Price) in Linear regression we have to choose @0, @1 so that ho(x) is close to y for our training examples (x,y)
-
Machine learning - created from Mind Map Supervised learning Unsupervised learning Reinforcement learning
-
normal equation direct solution method: h(theta) =[theta] * [X] [theta] =(X-transpose X) -Inverse * X-transpose * y
More Machine Learning resources
About machine learning notes
GoConqr OriginalUsing machine learning notes
Start with Machine Learning Types by Task for an overview of classification, clustering and prediction. It also introduces the bias-variance trade-off. If you are focusing on regression, the notes on multivariate and polynomial regression offer examples of each approach.
For dimensionality reduction, Principal Component Analysis covers geometric intuition, the objective function and eigenvalues and eigenvectors. The notes on dimensionality reduction and visualisation also cover data matrices and feature normalisation. Read them alongside the PCA notes when you want to review how a dataset is represented.
Revise with notes
Read a short section, then write down its main ideas in your own words. Return to the note to check what you included. For a different way to revisit a topic, switch to a mind map or quiz on the unit page. Choose a topic and open the notes that match it.
Frequently asked questions
Which notes are a useful starting point?
Machine Learning Types by Task is a useful starting point if you want to review classification, clustering and prediction together. For a more focused topic, try Principal Component Analysis, which covers geometric intuition and the mathematical objective. You can then choose another note that matches the topic you are studying.
Are these notes free to use?
Yes. Every note listed here is free to open and study without an account. The notes were made by GoConqr users. A free account also lets you save quiz scores and make your own quizzes, mind maps, flashcards and notes for your revision or teaching.
What topics do the notes cover?
The notes cover topics including classification, clustering, prediction, regression and dimensionality reduction. Machine Learning with Spark summarises supervised classification and regression problems and unsupervised clustering and association problems. Other notes cover Bayesian networks, principal component analysis and the bias-variance trade-off.