601 тысяч подписчиков
421 видео
Neural Networks 1: a 3-minute history
Neural Networks 2: machine learning = feature engineering
Neural Networks 3: axons, dendrites, synapses
Neural Networks 4: McCulloch & Pitts neuron
Neural Networks 5: feedforward, recurrent and RBM
Neural Networks 6: solving XOR with a hidden layer
Neural Networks 7: universal approximation
Neural Networks 8: hidden units = features
Neural Networks 9: derivatives we need for backprop
Backpropagation: how it works
Neural Networks 11: Backpropagation in detail
Neural Networks 12: multiclass classification
Relevance model 7: ranking functions
PCA 11: linear discriminant analysis
IR4.3 How to tokenize text
Clustering 3: Types of clustering algorithms
LSH.9 Locality-sensitive hashing: how it works
IR2.2 Zipf's law
IAML2.4: What is regression?
Indexing 4: phrases and proximity
LM.2 What is a language model?
kNN.12 Parzen windows, kernels and SVM
Clustering 6: how many clusters?
k-NN 9: inverted index
Agglomerative Clustering: how it works
IAML8.13 False positives and false negatives
Text Classification 1: Centroid Method
IAML2.20: Supervised vs unsupervised learning
LSH.8 Locality-sensitive hashing: the idea
IR3.2 Overview of the vector space model
IAML5.2: Bayesian classification
k-NN 5: resolving ties and missing values
Indexing 8: doc-at-a-time query execution
kNN.14 Computational complexity of finding nearest-neighbors
Evaluation 17: statistical significance test
EM algorithm: how it works
K-means clustering: how it works
IR4.6 Stemming algorithms
IR4.23 Pseudo-relevance feedback
Indexing 7: v-byte encoding (compression)
Clustering 11: Paired evaluation and Rand index
LM.12 Smoothing and inverse document frequency
PCA 10: eigen-faces
IAML2.21: Binary vs. multiclass classifiers
Web crawling 1: sources of data
Indexing 1: what makes google fast
Indexing 2: inverted index
Indexing 5: XML, structure and metadata
IR4.13 Finding synonyms in Wordnet
IR4.8 Character n-grams
Web crawling 4: inside an HTTP request
Web crawling 2: blogs, tweets, news feeds
PCA 5: Feature selection and feature extraction
