Deep Learning with Tensorflow and Angular 2!

Launch into Java language basics in Android Studio by exploring variables, data types, and conversion; learn arrays and lists, control flow, loops, functions, and class structure with modifiers.

Explore Java variable types from integers and longs to floats, doubles, booleans, chars, and strings, and learn declaration and initialization, default values, and the difference between primitive types and strings.

Explore primitive types and strings, assignments, arithmetic and conditional operators, and basic conversions. Learn type casting, string concatenation, and parsing strings to numbers using standard methods.

Explore arrays and lists in Java, highlighting immutability of arrays versus the mutable nature of lists, including array and ArrayList setup, initialization, and basic operations.

Access and modify array and array list elements using zero-based indices, check length to prevent out-of-bounds errors, and explore get, set, and remove operations.

Explore control flow with if and switch statements, including else if, nested ifs, default cases, and the and/or operators, via a traffic light example.

Master while loops as a core control flow that repeats code until a condition is false, enabling tallying numbers and iterating arrays, with break and continue to avoid infinite loops.

Explore for loops and for-each variants, and compare them with while loops for safe array iteration. See how a balance is calculated from a list of transactions using these loops.

Learn how to declare, implement, and call functions in Java, cover return types, parameters, function bodies, and a bank purchase example including access modifiers and basic control flow.

Explore functions with parameters and return values, using promises, boolean return, and double cost to model purchases; learn type-based function overloading and variable scope.

Explore the basics of classes and objects in Java, including fields, methods, constructors, and the blueprint and object relationship that defines state and behaviors.

Explore how a subclass inherits all attributes and methods from a superclass, adds new behavior like strobe settings, and overrides methods to customize lights.

Learn static variables and access modifiers in Java, including class-level constants accessed via the class name, and how private access and encapsulation are achieved with methods.

Learn to build an Android app from start to finish by designing the UI with XML files, wiring the UI to backend code, and testing on the emulator.

Build and position a basic Android UI using constraint layout, edit text, and text view, then wire up string resources and on click to display results.

Connect UI elements to the backend by linking edit text and text view to the main activity, retrieving and displaying text, and wiring the button click to show results.

Process user input text and display it in the text view, handling empty input gracefully. Then tailor Android user interface by adjusting background colors, text sizes, padding, and constraint layouts.

Explore Python fundamentals quickly by downloading the latest Python version, inspecting the interface, and learning core language basics to build, run, and debug projects in this two-part series.

Download and install PyCharm community edition and the latest Python 3.x, preferably 3.6.x, then create a new PyCharm project in a specified folder and set up a virtual environment.

Explore the PyCharm interface to create, open, and manage Python files, set up project interpreters, run code, and install packages.

Explore how variables store values in python, cover integers, floats, booleans, and strings, and learn about type inference, print and type functions, and None for no value.

Explore assignment and not operators, arithmetic and conditional operators, modulus and double divide, and string concatenation, then learn how to convert between integers, floats, and strings in Python.

Explore Python collections by examining tuples, lists, and dictionaries, and learn how to store, index, and access multiple values using positional indices and keys.

Explore operations on tuples, lists, and dictionaries, including retrieving, modifying, concatenating, deleting elements, and using length, min, max, and dictionary methods like keys, values, and items.

Master control flow with if statements and else branches, using bank balance examples to illustrate transactions. Preview loops, including while and for in / for each, to support iteration.

Explore while loops and for loops in Python, learning to repeat tasks until a condition fails and to break or continue while traversing arrays.

Discover how to declare, implement, and call functions in Python, pass parameters, return values, and use promises, while managing starting and current positions in example scenarios.

Explore how classes act as blueprints for objects, with attributes and methods, and how initialisers create new instances and manage state and behavior in Python.

Begin with TensorFlow basics, learn what it is, install it into Python, and build training and testing models, culminating in a linear regression from scratch.

Explore the key TensorFlow components to build a computational graph and train and test a model. Follow along to build a simple linear regression model in Python.

Import TensorFlow in PyCharm, set the tf alias, and troubleshoot installation by locating site-packages and configuring the interpreter to build a graph with constants and tensors.

Explore constant nodes for storing unchanging values in a TensorFlow graph, and learn to run them with sessions to print and inspect their current tensor values.

Explore constant nodes and sessions in the Tensorflow computational graph, store unchanging values, define shapes and data types, and run nodes to view their current values.

Explore variable nodes, how they differ from constant notes, and how manual reassignment and training update their values in a graph.

Explore placeholder nodes as input points in computational graphs, assign values at runtime via feed dictionaries, and enforce shape and data type constraints for reliable model training and testing.

Explore operation nodes that perform calculations on existing nodes, building a mini computation graph with constants, placeholders, and variables, using both TensorFlow nodes and arithmetic operators.

Learn how loss functions measure the gap between actual and expected outputs. Apply optimizers, including gradient descent, to minimize loss during training and testing of a linear regression model.

Build a linear regression model in TensorFlow using w x plus b, with placeholders, trainable weights and biases, and gradient descent to minimize loss on simulated data.

Save a pre-trained model, import it into Android Studio, and build an app that uses TensorFlow to predict digits from NIST data.

Explore tensor flow estimator to build and evaluate machine learning models in Python. Compare estimator approaches with a basic linear regression and discuss built-in versus slightly customized methods.

Explore building a linear regression model with TensorFlow’s estimator, compare built-in versus custom estimation approaches, and learn how features drive input functions for training, testing, and evaluation.

Set up a prebuilt estimator model using TensorFlow's linear regression, define a single feature column, and prepare training and evaluation inputs with input functions for a streamlined workflow.

Train with a prebuilt linear regression model, evaluate on test data, and generate predictions using dedicated input functions and an estimator.

Learn to build a custom estimator function in TensorFlow, defining a model function with features, labels, loss, and a gradient-descent optimizer, then train and evaluate with custom input data.

Compare a custom estimator function to a prebuilt model in a deep learning workflow, covering training, evaluation, prediction, and debugging of mode handling, input defaults, and float types.

Compare three linear regression models: prebuilt estimator-based, custom input functions, and basic linear regression, and weigh lines of code, training, testing, and loss to reveal tradeoffs between simplicity and customization.

Explore end-to-end mobile machine learning with TensorFlow: train a linear regression model in Python, export the model to Android Studio, and build a simple Android app that demonstrates real-time predictions.

Learn how to import a pre-trained linear regression model into an Android Studio app, build a simple UI, and test the integrated model on an emulator.

Format the TensorFlow graph by naming nodes and using explicit multiply and add operations, then save the graph definition and trained values to protobuf and checkpoint files for reuse.

Freeze the TensorFlow graph and save an optimized protobuf file for Android Studio import, using freeze_graph and optimize_for_inference to produce a frozen linear regression model.

Set up an Android Studio project, import the optimized frozen model and inference library, configure SDK versions, and prepare assets and main activity to connect the UI with the model.

Design a simple Android UI that accepts a number and shows the result, wire it to main activity, and configure TensorFlow inference inputs, outputs, input shape, and library loading.

Initialize a TensorFlow inference interface, prepare a float input, run inference on the model, and display the resulting output in the text view after pressing the button.

Test your deep learning app by debugging inference, fixing null pointer and input errors, and validating emulator API compatibility to ensure a stable Android deployment of your TensorFlow model.