Hands-On Machine Learning: Learn TensorFlow, Python, & Java!

Learn to set up Android Studio, explore its interface, and write basic Java syntax to build a simple input-output Android app from start to finish.

download and install android studio on mac, set up sdk components, and create a new project with a chosen api level and main activity.

Explore Android Studio's interface, navigate the project structure, edit activity and layout files, and learn about resources, Gradle scripts, comments, and log statements, preparing to run on an emulator.

Learn to set up an Android emulator in Android Studio, create a virtual device, build and run your app, and understand emulator limits versus real devices.

Explore Java language basics in Android Studio by learning variables, types, and type conversion; master arrays, lists, collections, control flow, functions, and classes with fields, constructors, and inheritance.

Explore variables in java by examining primitive types: integers, longs, floats, doubles, booleans, characters, and strings. Learn declaration, initialization, default values, and basic operations and conversions for strong typing.

Explore operations on variables, including assignment, not, arithmetic, modulus, and concatenation. Learn type casting and conversions between strings and numbers.

Compare arrays and lists in Java, showing how to set up and initialize immutable arrays versus mutable lists, and explain basic operations and common implementations like array list.

This lecture covers array and array list operations, including zero-based indexing, length checks to avoid out-of-bounds errors, and basic get, set, remove, and clear methods.

Learn control flow with if and switch statements, including else and else if, plus nested tests and logical operators. See traffic light and speed examples to practice condition testing.

Master while loops and drive repeated execution until a condition fails. Apply them to tally numbers, manage indices, use break and continue, and prepare for array iteration and for loops.

Learn how to use for loops and for each loops to iterate through arrays and sum transactions into a balance, and compare with while loops for safe bounds.

Learn how to declare, implement, and call functions in Java, using a bank transaction example to illustrate return types, parameters, function bodies, and calling functions from code.

Learn how functions are defined by name, return type, and parameters, and how promises serve as inputs to produce return values, including boolean and double examples.

Learn the basics of classes and objects in Java, including fields, methods, and constructors. Create new instances and access their state and behavior using dot syntax.

Explore the subclass–superclass relationship by building a strobe light class that extends a generic light, inheriting attributes and methods, overriding behavior, and adding new strobe settings and constructors.

Explore static variables versus instance variables and understand access modifiers like private, public, protected, and default, including class name access and encapsulation in Java.

Learn to build an end-to-end android app by designing the UI with xml, connecting it to java code, implementing backend calculations, and testing on the emulator to improve the UI.

Learn to build an Android UI using constraint layout, adding an edit text, text view, and button, set constraints, and use string resources and hints to display results.

Connect the ui to the backend by accessing edit text and text view in the main activity, then display results by getting and setting text via an on click method.

Develop and display user-entered text in a simple Android app by implementing a core text processing function, handling empty input, and styling the UI with color and layout tweaks.

Learn to download, install, and set up PyCharm and Python, explore the PyCharm interface, and start building, running, and debugging Python projects while covering Python fundamentals.

download and install PyCharm community edition and Python 3.x, then set up the IDE, verify the installation, and create a new project with a virtual environment.

Explore the PyCharm interface, create and open Python files, run programs, and manage the project interpreter and packages, including installing TensorFlow for machine learning projects.

Explore variables in Python, learn how integers, floats, booleans, and strings store values, how type is inferred, and how None represents no value.

Master variables and operators in Python, covering assignment, not, arithmetic, division, modulus, and string concatenation with practical examples. Explore type conversions between int, float, and string, including compound assignments.

Explore Python collections—tuples, lists, and dictionaries—learning how to store multiple values, access elements by index or key, and understand when dictionaries offer precise data mapping.

Explore tuples, lists, and dictionaries operations by retrieving, modifying, adding, and deleting elements; compute length, min, max, and access keys, values, and items with append, pop, and clear.

Learn how control flow uses if statements to make decisions, with else and else-if branches, nesting, and logical operators to test multiple conditions in code.

Master using while and for loops to automate repetitive tasks, iterate through arrays, and control flow with break and continue, while avoiding endless loops.

Discover how to declare, implement, and call functions in Python, pass arguments and promises, and return values to control game character movement and track positions.

Learn how classes provide blueprints for objects, and how objects store state and behavior in Python. Explore initializers, attributes, and methods, and create new instances with a game character example.

Explore TensorFlow basics, install and import TensorFlow into Python, and build training and testing machine learning models with Python code. Finish by creating a real linear regression model from scratch.

Learn to use TensorFlow in Python to build a computational graph, format data, and train and test a simple linear regression model, exploring nodes, tensors, and common components.

Create a python file, import TensorFlow as tf, and configure PyCharm to access TensorFlow for pie chart project, troubleshooting installation and setting the project interpreter to build a computational graph.

Learn how constant nodes store unchanging values in a computation graph, define value, data type, and shape, and use sessions to run nodes and fetch current values.

Explore variable nodes, how they differ from constant nodes, and how their values can change during training or by manual reassignment, using TensorFlow's global variables initializer.

Learn how placeholder nodes act as inputs in computational graphs, requiring runtime values via feed dictionaries and respecting shape and data type constraints.

Create a mini computational graph with operation nodes, using constants, placeholders, and variables, perform add and multiply operations, and feed placeholders via a feed dictionary in TensorFlow.

Explore loss functions and optimizers, and how training uses gradient descent with a learning rate to minimize loss while testing on separate data, as a linear regression setup.

Builds a linear regression model in Python using a computational graph, defines w and b, placeholders for x and y, squared loss, and gradient descent training loop to fit data.

Create a simple MNIST digit recognizer using TensorFlow and Python, starting with a linear regression model to predict digits from images and later porting to an Android UI.

Explore the MNIST data set and understand image and label formats for digit recognition. Build a Python linear regression model, train and test, then export it for Android Studio predictions.

Build a TensorFlow style computational graph with placeholders for 784-element inputs and 10-element labels, computing 10 outputs and training with cross-entropy loss via gradient descent.

Train and test a TensorFlow model by running a training loop with batches, evaluating accuracy, and generating predictions, then prepare for saving and freezing the graph.

Save the graph to a checkpoint and a text file, then freeze it to produce an optimized frozen model for Android import.

Set up an Android Studio project for a TensorFlow inference app, import the optimized model and assets, configure API 25, and prepare input/output nodes for emulator testing.

Build a bare-bones Android user interface with constraint layout, featuring an image view, two buttons, and a results text view, wired to main activity for backend integration.

Learn to load and cycle through digit images (0–9) using resource IDs, display them in an image view, and prepare for resizing before model prediction.

Format image data by converting 28x28 bitmaps to a 784-element float array, resizing when needed, and preparing pixel buffers for model prediction of handwritten digits.

Feed image pixel buffers into a trained model, run inference via an inference interface, and extract a 10-element float prediction array, then log and prepare readable outputs.

Display and format the model's top two predictions in the app by computing the maximum and second-maximum indices from the inference results, then show them in the text view.