Современные достижения и перспективы Робототехники и Искусственного Интеллекта

Директор лаборатории Искусственного Интеллекта Стенфорда Эндрю Энг рассказывает о современных достижениях и перспективах Искусственного Интеллекта. Значительную часть доклада он посвещает искусственным нейронным сетям.

Machine Learning Algorithms

Supervised Learning

Linear Regression (Hypothesis, Uni-variable, Cost-function, Gradient Descent, Multivariable, Feature Scaling, Mean normalization)

Polynomial Regression

Normal Equation (Algorithm, Comparison with Gradient Descent, Case with Non-invertability matrix )

Logistic Regression for Classification (Hypothesis, Non-linear decision boundaries, Cost-function, Simplified cost-function and Gradient Descent)

Advanced Optimization

Advanced Algorithms (Conjugate Gradient, BFGS, L-BFGS)

Multi-class classification: One-vs-all

Regularization: Over-fitting problem, Cost-function, Linear Regression, Normal Equation, Logistic Regression, Advanced Algs)

Take away from AI-Class



Supervised Learning


Spam Detection (with Naive Bayes)

Maximum Likelihood

Laplace Smoothing

Advanced SPAM filtering

Handwriting classification

Overfitting prevetion

Linear Regression


Perceptron Algorithm

Maximum Margin Algorithms (SVM, Boosting)

K-nearest neighbors (Algorithm, Problems)

Unsupervised Learning

Density estimation, Dimensionality Reduction, Blind sequence separation, Factor Analysis


k-means (algorithm, problems)

Expectation minimization

Gaussians and Normal Distribution

Gaussian Learning


# of cluster calculation

Dimensionality Reduction

Spectral Clustering

Machine Learning Intro

Machine Learning is the instrument to “learn” models from data (i.e. inferring Bayes Networks from the available data).  Machine Learning algorithms/approaches could be identified by following aspects.

How they defined: Parameters, Structure, Hidden concepts

How they learn: Supervised, Unsupervised, Reinforcement learning

What they are used for: Prediction, Diagnostics, Summarization, etc.

How learning is done: Passive, Active, Online, Offline.

Outputs: Regression Vs. Classification

Notes from AI Class in Stanford