book

Artificial Intelligence with Python Cookbook

by Ritesh Kumar, Ben Auffarth

October 2020

Beginner to intermediate

468 pages

9h 39m

English

Packt Publishing

Read now

Unlock full access

Artificial Intelligence with Python Cookbook
Why subscribe?
About the authorAbout the reviewersPackt is searching for authors like you
Who this book is forWhat this book coversTo get the most out of this bookDownload the example code filesDownload the color imagesConventions usedSectionsGetting readyHow to do it…How it works…There's more…See alsoGet in touchReviews
Technical requirementsSetting up a Jupyter environmentGetting readyHow to do it...Installing libraries with Google ColabSelf-hosting a Jupyter Notebook environmentHow it works...There's more...See alsoGetting proficient in Python for AIGetting readyHow to do it...Obtaining the history of Jupyter commands and outputsExecution historyOutputsAuto-reloading packagesDebuggingTiming code executionDisplaying progress barsCompiling your codeSpeeding up pandas DataFramesParallelizing your codeSee alsoClassifying in scikit-learn, Keras, and PyTorchGetting readyHow to do it...Visualizing data in seabornModeling in scikit-learnModeling in KerasModeling in PyTorchHow it works...Neural network trainingThe SELU activation functionSoftmax activationCross-entropySee alsoModeling with KerasGetting readyHow to do it...Data loading and preprocessingModel trainingHow it works...Maximal information coefficientData generatorsPermutation importanceSee also
Technical requirementsTransforming data in scikit-learnGetting readyHow to do it...Encoding ranges numericallyDeriving higher-order featuresCombining transformationsHow it works...There's more...See alsoPredicting house prices in PyTorchGetting readyHow to do it...How it works...There's more...See alsoLive decisioning customer valuesGetting readyHow to do it...How it works...Active learningHoeffding TreeClass weightingSee alsoBattling algorithmic biasGetting readyHow to do it...How it works...There's more...See alsoForecasting CO2 time seriesGetting readyHow to do it...Analyzing time series using ARIMA and SARIMAHow it works...There's more...See also
Clustering market segmentsGetting readyHow to do it...How it works...There's more...See alsoDiscovering anomaliesGetting readyHow to do it...How it works...k-nearest neighborsIsolation forestAutoencoderSee alsoRepresenting for similarity searchGetting readyHow to do it...Baseline – string comparison functionsBag-of-characters approachSiamese neural network approachHow it works...Recommending productsGetting readyHow to do it...How it works...Precision at kMatrix factorizationThe lightfm modelSee alsoSpotting fraudster communitiesGetting readyHow to do it...Creating an adjacency matrixCommunity detection algorithmsEvaluating the communitiesHow it works...Graph community algorithmsLouvain algorithmGirvan–Newman algorithmInformation entropyThere's more...See also
Technical requirementsPredicting stock prices with confidenceGetting readyHow to do it...How it works...FeaturizationPlatt scalingIsotonic regressionNaive BayesSee alsoEstimating customer lifetime valueGetting readyHow to do it...How it works...The BG/NBD modelThe Gamma-Gamma modelSee alsoDiagnosing a diseaseGetting readyHow to do it...How it works...Aleatoric uncertaintyNegative log-likelihoodBernoulli distributionMetricsSee alsoStopping credit defaultsGetting readyHow to do it...How it works...Epistemic uncertaintySee also
Making decisions based on knowledgeGetting readyHow to do it...Logical reasoningKnowledge embeddingHow it works...Logical reasoningLogic proversKnowledge embeddingGraph embedding with WalkletsSee alsoSolving the n-queens problemGetting readyHow to do it...Genetic algorithm Particle swarm optimizationSAT solverHow it works...Genetic algorithmParticle swarm optimizationSAT solverSee alsoFinding the shortest bus routeGetting readyHow to do it...Simulated annealingAnt colony optimizationHow it works...Simulated annealingAnt colony optimizationSee alsoSimulating the spread of a diseaseGetting readyHow to do it...How it works...There's more...See alsoWriting a chess engine with Monte Carlo tree searchGetting readyHow to do it...Tree searchImplementing a nodePlaying chessHow it works...There's more...See also

Technical requirementsOptimizing a websiteHow to do it...How it works...See alsoControlling a cartpoleGetting readyHow to do it...How it works...There's more...Watching our agents in the environmentUsing the RLlib librarySee also Playing blackjackGetting readyHow to do it...How it works...See also
Technical requirementsRecognizing clothing itemsGetting readyHow to do it...Difference of GaussiansMultilayer perceptronLeNet5MobileNet transfer learningHow it works...Difference of GaussianLeNet5MobileNet transfer learningSee alsoGenerating imagesGetting readyHow to do it...How it works...See alsoEncoding images and styleGetting readyHow to do it...How it works...See also
Technical requirementsLocalizing objectsGetting readyHow to do it...How it works...There's more...See alsoFaking videosGetting readyHow to do it...How it works...See alsoDeep fakesDetection of deep fakes
Technical requirementsRecognizing voice commandsGetting readyHow to do it...How it works...See alsoSynthesizing speech from textGetting readyHow to do it...How it works...Deep Convolutional Networks with Guided AttentionWaveGANThere's more...See alsoGenerating melodiesGetting readyHow to do it...How it works...See also
Technical requirementsClassifying newsgroupsGetting readyHow to do it...Bag-of-wordsWord embeddingsCustom word embeddingsHow it works...The CBOW algorithmTFIDFThere's more...See alsoChatting to usersGetting readyHow to do it...How it works...ELIZAEywaSee alsoTranslating a text from English to GermanGetting readyHow to do it...How it works...There's more...See alsoWriting a popular novelGetting readyHow to do it...How it works...See also
Technical requirementsVisualizing model resultsGetting readyHow to do it...Streamlit hello-worldCreating our data appHow it works...See alsoServing a model for live decisioningGetting readyHow to do it...How it works...MonitoringSee alsoSecuring a model against attackGetting readyHow to do it...How it works...Differential privacyPrivate aggregation of teacher ensemblesSee also
Leave a review - let other readers know what you think

Content preview from Artificial Intelligence with Python Cookbook

Artificial Intelligence in Production

In the creation of a system that involves artificial intelligence (AI), the actual AI usually only takes a small fraction of the total amount of work, while a major part of the implementation entails the surrounding infrastructure, starting from data collection and verification, feature extraction, analysis, resource management, and serving and monitoring (David Sculley and others. Hidden technical debt in machine learning systems, 2015).

In this chapter, we'll deal with monitoring and model versioning, visualizations as dashboards, and securing a model against malicious hacking attacks that could leak user data.

In this chapter, we'll be covering the following recipes: