Index
A
- accuracy / Evaluation of the model
- agent / Reinforcement learning
- algorithms
- about / Introduction to algorithms
- decision tree / Decision tree
- random forests / Random forests
- Android app
- creating / Creating the Android app
- TF Model, copying / Copying the TF Model
- activity, creating / Creating an activity
- android application, creating with fritz pre-built models
- about / Creating an android application using fritz pre-built models
- dependencies, adding / Adding dependencies to the project
- Fritz JobService, registering / Registering the Fritz JobService in your Android Manifest
- app layout and components, creating / Creating the app layout and components
- application, coding / Coding the application
- Artificial Intelligence (AI)
- about / Where is data science used?, What is AI?
- general AI / What is AI?
- narrow AI / What is AI?
- relationship, with data science / How are data science, AI, and machine learning interrelated?
- artificial neural networks (ANNs) / What are artificial neural networks?
- assignment problem statement / Image recognition solution
- association-rule learning algorithm / Association rule learning algorithm
B
- batch prediction / Core ML
- bias / Evaluation of the model
- big data
- volume / What is big data?
- velocity / What is big data?
- variety / What is big data?
- Bluetooth Low Energy (BLE) / E-commerce
- Boston
- dataset naming / Dataset naming
- Breast Cancer dataset
- about / Dataset
- naming / Naming the dataset
C
- Caffe2
- reference / Caffe2
- Carat / Carat
- Classification and Regression Trees (CART) / Decision trees
- classification tree / Decision tree
- clustering algorithms
- similarity function / Clustering algorithms
- clustering methods
- about / Clustering methods
- hierarchical agglomerative / Hierarchical agglomerative clustering methods
- K-means clustering / K-means clustering
- confusion matrix / Evaluation of the model
- Conv Nets
- reference / Retraining the model
- convolutional neural networks (CNNs) / Understanding the model concepts
- Core ML
- basics / Understanding the basics of Core ML
- problem solving, with linear SVM / Solving the problem using linear SVM in Core ML
- Core ML model, using with Fritz
- about / Using the existing Core ML model in an iOS application using Fritz
- account, signing up / Registering with Fritz
- account, logging in / Creating a new project in Fritz
- model file (.pb or .tflite), uploading / Uploading the model file (.pb or .tflite)
- Xcode project, creating / Creating an Xcode project
- code, adding / Adding code
- iOS mobile application, building / Building and running the iOS mobile application
- iOS mobile application, executing / Building and running the iOS mobile application
- cross-validation / Evaluation of the model
D
- Dango / Dango
- data mining / What is data mining?
- data science
- about / Data science, What is data science?
- using / Where is data science used?
- and big data, relationship / Relationship between data science and big data
- decision trees
- internal node / Decision trees
- edges / Decision trees
- leaf / Decision trees
- about / Decision tree
- advantages / Advantages of the decision tree algorithm, Advantages of decision trees
- purity parameter / Advantages of the decision tree algorithm
- disadvantages / Disadvantages of decision trees
- directed acyclic graphs (DAGs) / Decision tree
E
- error / Evaluation of the model
- error matrix / Evaluation of the model
F
- Facebook / Facebook
- face detection
- concepts / Face detection concepts
- solution, obtaining with ML Kit / Sample solution for face detection using ML Kit
- face orientation / Face detection concepts
- face recognition / Face detection concepts
- face tracking / Face detection concepts
- feature engineering
- about / Introducing NLP, Feature engineering
- entity extraction / Entity extraction
- topic modeling / Topic modeling
- bag-of-words model / Bag-of-words model
- Statistical Engineering / Statistical Engineering
- TF-IDF / TF–IDF, TF-IDF
- TF / TF
- Inverse Document Frequency (IDF) / Inverse Document Frequency (IDF)
- features, Google Cloud Vision
- label detection / Features of Google Cloud Vision
- image attribute detection / Features of Google Cloud Vision
- face detection / Features of Google Cloud Vision
- logo detection / Features of Google Cloud Vision
- landmark detection / Features of Google Cloud Vision
- optical character recognition / Features of Google Cloud Vision
- Explicit Content Detection / Features of Google Cloud Vision
- Search Web / Features of Google Cloud Vision
- fine needle aspirate (FNA) / Dataset
- Firebase on-cloud APIs
- used, for creating text recognition app / Creating a text recognition app using Firebase on-cloud APIs
- Firebase on-device APIs
- used, for creating text recognition app / Creating a text recognition app using Firebase on-device APIs
- reference / Creating a text recognition app using Firebase on-device APIs
- forecasting problem / Introduction to regression
- Fritz
- about / Introduction to Fritz
- prebuilt ML models / Prebuilt ML models
- custom models, using / Ability to use custom models
- model management / Model management
- using, examples / Hand-on samples using Fritz
- existing TensorFlow for mobile model, using / Using the existing TensorFlow for mobile model in an Android application using Fritz
- registering with / Registering with Fritz, Setting up Android and registering the app
- model file (.pb or .tflite), uploading / Uploading the model file (.pb or .tflite)
- setting up, in Android / Setting up Android and registering the app
- TFMobile library, adding / Adding Fritz's TFMobile library
- dependencies, adding / Adding dependencies to the project
- building / Building and running the application
- executing / Building and running the application
- new version of model, deploying / Deploying a new version of your model
- using, with Core ML model / Using the existing Core ML model in an iOS application using Fritz
- Fritz Interpreter
- TensorFlowInferenceInterface class, replacing with / Replacing the TensorFlowInferenceInterface class with Fritz Interpreter
- FritzJob service
- registering, in Android Manifest / Registering the FritzJob service in your Android Manifest
G
- GBoard / GBoard
- Google Cloud Vision
- features / Features of Google Cloud Vision
- reference / Features of Google Cloud Vision
- used, for creating mobile application / Sample mobile application using Google Cloud Vision
- Google Maps / Google Maps
H
- handwritten digit-recognition problem
- hyperplane / Introduction to regression
I
- IKEA Pace
- reference / Real estate
- ImprompDo / ImprompDo
- indoor navigation / E-commerce
- innovation areas
- about / Key innovation areas
- personalization applications / Personalization applications
- healthcare / Healthcare
- targeted promotions and marketing / Targeted promotions and marketing
- visual and audio recognition / Visual and audio recognition
- e-commerce / E-commerce
- finance management / Finance management
- gaming and entertainment / Gaming and entertainment
- enterprise apps / Enterprise apps
- real estate / Real estate
- agriculture / Agriculture
- energy / Energy
- mobile security / Mobile security
- installations
- about / Installation
- Python / Python
- Python dependencies / Python dependencies
- Xcode / Xcode
- Inverse Document Frequency (IDF) / Inverse Document Frequency (IDF)
- iOS Mobile application
- writing / Writing the iOS mobile application
K
- Keras
- about / Introduction to Keras
- uses / Introduction to Keras
- reference / Introduction to Keras
- installing / Installing Keras
- Keras model
- building, with sequential API / Defining the model's architecture
- Kernel Trick / Understanding linear SVM algorithm
L
- landmark / Face detection concepts
- learning
- types / Types of learning
- supervised learning / Supervised learning
- unsupervised learning / Unsupervised learning
- semi-supervised learning / Semi-supervised learning
- reinforcement learning / Reinforcement learning
- challenges / Challenges in machine learning
- linear regression
- about / Linear regression, Linear regression
- dataset / Dataset
- dataset naming / Dataset naming
- Linear SVM algorithm
- about / Understanding linear SVM algorithm
- used, for problem solving in Core ML / Solving the problem using linear SVM in Core ML
- logistic regression / Logistic regression
M
- machine learning
- defining / Definition of machine learning
- using, scenarios / When is it appropriate to go for machine learning systems?
- process / The machine learning process
- issue, defining / Defining the machine learning problem
- model, building / Building the model
- predictions, deploying / Making predictions/Deploying in the field
- using, on mobile devices / Why use machine learning on mobile devices?
- on mobile, advantages / Why use machine learning on mobile devices?
- implementing, in mobile application / Ways to implement machine learning in mobile applications
- service providers, utilizing / Utilizing machine learning service providers for a machine learning model
- model, training / Ways to train the machine learning model
- training, on desktop / On a desktop (training in the cloud)
- training, on device / On a device
- inference process, on server / Ways to carry out the inference – making predictions
- process, on device / Ways to carry out the inference – making predictions, Inference on a device
- process, on server / Inference on a server
- mobile tools / Popular mobile machine learning tools and SDKs
- SDKs / Popular mobile machine learning tools and SDKs
- relationship, with data science / How are data science, AI, and machine learning interrelated?
- machine learning framework
- about / Machine learning framework
- Caffe2 / Caffe2
- scikit-learn / scikit-learn
- TensorFlow / TensorFlow
- Core ML / Core ML
- market-basket analysis / Association rule learning algorithm
- maximum-margin classifier / Support vector machines
- maximum-margin hyperplane / Support vector machines
- ML Kit
- about / Understanding ML Kit
- machine learning scenarios / Understanding ML Kit
- APIs / ML Kit APIs
- used, for face detection / Face detection using ML Kit
- used, for finding solution for face detection / Sample solution for face detection using ML Kit
- app, executing / Running the app
- ML Kit APIs
- about / ML Kit APIs
- text recognition / Text recognition
- face detection / Face detection
- barcode scanning / Barcode scanning
- image labeling / Image labeling
- landmark recognition / Landmark recognition
- custom model inference / Custom model inference
- ML mobile applications
- about / Key ML mobile applications
- Facebook / Facebook
- Google Maps / Google Maps
- Snapchat / Snapchat
- Tinder / Tinder
- Netflix / Netflix
- Oval Money / Oval Money
- ImprompDo / ImprompDo
- Dango / Dango
- Carat / Carat
- Uber / Uber
- GBoard / GBoard
- MNIST
- reference / Defining the problem statement
- mobile application, creating with Google Cloud Vision
- label detection, working / How does label detection work?
- prerequisites / Prerequisites
- key activities / Preparations
- working / Understanding the Application
- output / Output
- mobile machine learning application
- architecture / The architecture of a mobile machine learning application
- model concepts / Understanding the model concepts
- mobile machine learning project implementation
- about / Mobile machine learning project implementation
- high-level important items, considering / What are the high-level important items to be considered before starting the project?
- skills required / What are the roles and skills required to implement a mobile machine learning project?
- testing / What should you focus on when testing the mobile machine learning project?
- domain expert help / What is the help that the domain expert will provide to the machine learning project?
- pitfalls / What are the common pitfalls in machine learning projects?
- model building phase
- about / Building the model
- right machine learning algorithm, selecting / Selecting the right machine learning algorithm
- machine learning model, training / Training the machine learning model
- testing / Testing the model
- evaluating / Evaluation of the model
- multivariate regression problem / Introduction to regression
N
- Naive Bayes / Naive Bayes
- named entity recognition (NER) / Entity extraction
- natural language processing (NLP)
- about / Understanding NLP, Introducing NLP
- semantic information / Introducing NLP
- syntactic information / Introducing NLP
- pragmatic information (context) / Introducing NLP
- text, classifying/clustering / Classifying/clustering the text
- Netflix / Netflix
- neural networks
- about / Introduction to neural networks
- neuron, communications / Communication steps of a neuron
- activation function / The activation function
- neurons, arranging / Arrangement of neurons
- types / Types of neural networks
- neural networks / Types of neural networks
- CNN / Types of neural networks
- Recurrent Neural Networks / Types of neural networks
- implementation / Solving the problem
- handwritten digits recognition problem statement, defining / Defining the problem statement
- NLP processing / Introducing NLP
O
- on-device machine learning
- implementation, skills / Skills needed to implement on-device machine learning
- opportunities, for stakeholders
- hardware manufacturers / Hardware manufacturers
- mobile operating system vendors / Mobile operating system vendors
- third-party mobile ML SDK providers / Third-party mobile ML SDK providers
- ML mobile application developers / ML mobile application developers
- Oval Money / Oval Money
- overfitting / Evaluation of the model
P
- pandas
- reference / Creating the model file using scikit-learn
- plane / Introduction to regression
- prebuilt ML models, Fritz
- object detection / Prebuilt ML models
- image labeling / Prebuilt ML models
- precision / Evaluation of the model
- preprocessing / Introducing NLP
- Principal component analysis (PCA)
- reference / Deep dive into unsupervised learning algorithms
- Python
- reference / Python
Q
- quantization / Core ML
R
- random forest, Core ML
- used, for problem solving / Solving the problem using random forest in Core ML
- Breast Cancer dataset / Dataset
- requisites / Technical requirements
- model file, creating with scikit-learn / Creating the model file using scikit-learn
- scikit model, converting / Converting the scikit model to the Core ML model
- iOS mobile application, creating / Creating an iOS mobile application using the Core ML model
- random forests
- about / Random forest, Random forests
- applying, areas / Random forest
- comparing, with decision trees / Random forests
- recall / Evaluation of the model
- references / References
- refinements, face detection
- landmark detection / Face detection
- classification / Face detection
- regression analysis / Introduction to regression
- regression model
- used, for problem solving / Solving the problem using regression in Core ML
- creating, requisites / Technical requirements
- creating, with scikit-learn / How to create the model file using scikit-learn
- about / How to create the model file using scikit-learn
- testing / Running and testing the model
- executing / Running and testing the model
- importing, to iOS project / Importing the model into the iOS project
- iOS application, writing / Writing the iOS application
- iOS application, executing / Running the iOS application
- regression trees / Decision trees
- reinforcement learning / Reinforcement learning
- reinforcement signal / Reinforcement learning
- root mean squared error (RMSE) / How to create the model file using scikit-learn
S
- semi-supervised learning / Semi-supervised learning
- singular value decomposition (SVD)
- reference / Deep dive into unsupervised learning algorithms
- Snapchat / Snapchat
- soft margin / Support vector machines
- solution, handwritten digits recognition problem
- data, preparing / Preparing the data
- model's architecture, defining / Defining the model's architecture
- model, fitting / Compiling and fitting the model
- model, compiling / Compiling and fitting the model
- Keras model, converting to CoreML model / Converting the Keras model into the Core ML model
- iOS mobile application, creating / Creating the iOS mobile application
- spam message-detection problem
- solving / Solving the problem using linear SVM in Core ML
- data / About the data
- prerequisites / Technical requirements
- model file, creating with Scikit Learn / Creating the Model file using Scikit Learn
- Scikit-learn model, converting / Converting the scikit-learn model into the Core ML model
- iOS application, writing / Writing the iOS application
- stakeholders
- opportunities / Opportunities for stakeholders
- supervised learning
- about / Supervised learning, Deep dive into supervised learning algorithms
- classification problems / Deep dive into supervised learning algorithms
- regression problems / Deep dive into supervised learning algorithms
- supervised learning algorithms
- about / Introduction to supervised learning algorithms
- steps / Introduction to supervised learning algorithms
- exploring / Deep dive into supervised learning algorithms
- Naive Bayes / Naive Bayes
- decision trees / Decision trees
- linear regression / Linear regression
- logistic regression / Logistic regression
- support vector machine (SVM) / Support vector machines
- random forest / Random forest
- support vector classifier / Support vector machines
- support vector machine (SVM) / Support vector machines
T
- TensorFlow / An introduction to TensorFlow
- TensorFlow image-recognition model
- creating / Creating a TensorFlow image recognition model
- retraining / Retraining the model
- bottlenecks / About bottlenecks
- TensorFlow Lite
- comparing, with TensorFlow for mobile / An introduction to TensorFlow
- components / TensorFlow Lite components
- Inception V3 / Interface to hardware acceleration
- MobileNets / Interface to hardware acceleration
- on-device smart reply / Interface to hardware acceleration
- reference / Writing the mobile application using the TensorFlow model
- TensorFlow Lite components
- about / TensorFlow Lite components
- model-file format / Model-file format
- interpreter / Interpreter
- Ops/Kernel / Ops/Kernel
- interface to hardware acceleration / Interface to hardware acceleration
- TensorFlow mobile application
- writing, with TransferFlow model / Writing the mobile application using the TensorFlow model
- first program, writing / Writing our first program
- Android app, creating / Creating the Android app
- TensorFlow model
- used, for writing mobile application / Writing the mobile application using the TensorFlow model
- creating / Creating and Saving the TF model
- saving / Creating and Saving the TF model
- graph, freezing / Freezing the graph
- file, optimizing / Optimizing the model file
- converting, to CoreML Model / Converting the TensorFlow model into the Core ML model
- iOS Mobile application, writing / Writing the iOS mobile application
- tensor processing units (TPUs) / Creating a TensorFlow image recognition model
- Term Frequency-Inverse Document Frequency (TF-IDF) / Statistical Engineering
- text-preprocessing techniques
- about / Text-preprocessing techniques
- Noise, removing / Removing noise
- normalization / Normalization
- standardization / Standardization
- text recognition (OCR) model
- used, for creating text recognition app / Creating a text recognition app using Firebase on-device APIs
- text recognition app
- creating, with Firebase on-device APIs / Creating a text recognition app using Firebase on-device APIs, Creating a text recognition app using Firebase on-cloud APIs
- creating, with Firebase on-cloud APIs / Creating a text recognition app using Firebase on-cloud APIs
- Tinder / Tinder
- training data / Deep dive into supervised learning algorithms
U
- Uber / Uber
- underfitting / Evaluation of the model
- unsupervised learning
- used, for pattern detection / Unsupervised learning
- used, for descriptive modeling / Unsupervised learning
- Testing Phase / Unsupervised learning
- algorithms / Unsupervised learning
- unsupervised learning algorithms
- about / Introduction to unsupervised learning algorithms
- exploring / Deep dive into unsupervised learning algorithms
- clustering algorithms / Clustering algorithms
- clustering methods / Clustering methods
- association-rule learning algorithm / Association rule learning algorithm
V
- variance / Evaluation of the model