Complete A.I. & Machine Learning, Data Science Bootcamp
-
Introduction
-
Machine Learning 101What Is Machine Learning?0sAI/Machine Learning/Data Science0sZTM Resources0sExercise: Machine Learning Playground0sHow Did We Get Here?0sExercise: YouTube Recommendation Engine0sTypes of Machine Learning0sAre You Getting It Yet?What Is Machine Learning? Round 20sSection Review0sMonthly Coding Challenges, Free Resources and Guides
-
Machine Learning and Data Science FrameworkSection Overview0sIntroducing Our Framework0s6 Step Machine Learning Framework0sTypes of Machine Learning Problems0sTypes of Data0sTypes of Evaluation0sFeatures In Data0sModelling – Splitting Data0sModelling – Picking the Model0sModelling – Tuning0sModelling – Comparison0sOverfitting and Underfitting DefinitionsExperimentation0sTools We Will Use0sOptional: Elements of AI
-
The 2 Paths
-
Data Science Environment SetupSection Overview0sIntroducing Our Tools0sWhat is Conda?0sConda Environments0sMac Environment Setup0sMac Environment Setup 20sWindows Environment Setup0sWindows Environment Setup 20sLinux Environment SetupSharing your Conda EnvironmentJupyter Notebook Walkthrough0sJupyter Notebook Walkthrough 20sJupyter Notebook Walkthrough 30s
-
Pandas: Data AnalysisSection Overview0sDownloading Workbooks and AssignmentsPandas Introduction0sSeries, Data Frames and CSVs0sData from URLsQuick Note: Upcoming VideosDescribing Data with Pandas0sSelecting and Viewing Data with Pandas0sQuick Note: Upcoming VideosSelecting and Viewing Data with Pandas Part 20sManipulating Data0sManipulating Data 20sManipulating Data 30sAssignment: Pandas PracticeHow To Download The Course Assignments0s
-
NumPySection Overview0sNumPy Introduction0sQuick Note: Correction In Next VideoNumPy DataTypes and Attributes0sCreating NumPy Arrays0sNumPy Random Seed0sViewing Arrays and Matrices0sManipulating Arrays0sManipulating Arrays 20sStandard Deviation and Variance0sReshape and Transpose0sDot Product vs Element Wise0sExercise: Nut Butter Store Sales0sComparison Operators0sSorting Arrays0sTurn Images Into NumPy Arrays0sExercise: Imposter Syndrome0sAssignment: NumPy PracticeOptional: Extra NumPy resources
-
Matplotlib: Plotting and Data VisualizationSection Overview0sMatplotlib Introduction0sImporting And Using Matplotlib0sAnatomy Of A Matplotlib Figure0sScatter Plot And Bar Plot0sHistograms And Subplots0sSubplots Option 20sQuick Tip: Data Visualizations0sPlotting From Pandas DataFrames0sQuick Note: Regular ExpressionsPlotting From Pandas DataFrames 20sPlotting from Pandas DataFrames 30sPlotting from Pandas DataFrames 40sPlotting from Pandas DataFrames 50sPlotting from Pandas DataFrames 60sPlotting from Pandas DataFrames 70sCustomizing Your Plots0sCustomizing Your Plots 20sSaving And Sharing Your Plots0sAssignment: Matplotlib Practice
-
Scikit-learn: Creating Machine Learning ModelsSection Overview0sScikit-learn Introduction0sQuick Note: Upcoming VideoRefresher: What Is Machine Learning?0sQuick Note: Upcoming VideosScikit-learn: Cheatsheet0sTypical scikit-learn Workflow0sOptional: Debugging Warnings In Jupyter0sGetting Your Data Ready: Splitting Your Data0sQuick Tip: Clean, Transform, Reduce0sGetting Your Data Ready: Convert Data To Numbers0sNote: Update to next video (OneHotEncoder can handle NaN/None values)Getting Your Data Ready: Handling Missing Values With Pandas0sExtension: Feature ScalingNote: Correction in the upcoming video (splitting data)Getting Your Data Ready: Handling Missing Values With Scikit-learn0sNEW: Choosing The Right Model For Your Data0sNEW: Choosing The Right Model For Your Data 2 (Regression)0sQuick Note: Decision TreesQuick Tip: How ML Algorithms Work0sChoosing The Right Model For Your Data 3 (Classification)0sFitting A Model To The Data0sMaking Predictions With Our Model0spredict() vs predict_proba()0sNEW: Making Predictions With Our Model (Regression)0sNEW: Evaluating A Machine Learning Model (Score) Part 10sNEW: Evaluating A Machine Learning Model (Score) Part 20sEvaluating A Machine Learning Model 2 (Cross Validation)0sEvaluating A Classification Model 1 (Accuracy)0sEvaluating A Classification Model 2 (ROC Curve)0sEvaluating A Classification Model 3 (ROC Curve)0sReading Extension: ROC Curve + AUCEvaluating A Classification Model 4 (Confusion Matrix)0sNEW: Evaluating A Classification Model 5 (Confusion Matrix)0sEvaluating A Classification Model 6 (Classification Report)0sNEW: Evaluating A Regression Model 1 (R2 Score)0sNEW: Evaluating A Regression Model 2 (MAE)0sNEW: Evaluating A Regression Model 3 (MSE)0sMachine Learning Model EvaluationNEW: Evaluating A Model With Cross Validation and Scoring Parameter0sNEW: Evaluating A Model With Scikit-learn Functions0sImproving A Machine Learning Model0sTuning Hyperparameters0sTuning Hyperparameters 20sTuning Hyperparameters 30sNote: Metric Comparison ImprovementQuick Tip: Correlation Analysis0sSaving And Loading A Model0sSaving And Loading A Model 20sPutting It All Together0sPutting It All Together 20sScikit-Learn Practice
-
Supervised Learning: Classification + Regression
-
Milestone Project 1: Supervised Learning (Classification)Section Overview0sProject Overview0sProject Environment Setup0sOptional: Windows Project Environment Setup0sStep 1~4 Framework Setup0sNote: Code update for next videoGetting Our Tools Ready0sExploring Our Data0sFinding Patterns0sFinding Patterns 20sFinding Patterns 30sPreparing Our Data For Machine Learning0sChoosing The Right Models0sExperimenting With Machine Learning Models0sTuning/Improving Our Model0sTuning Hyperparameters0sTuning Hyperparameters 20sTuning Hyperparameters 30sQuick Note: Confusion Matrix LabelsEvaluating Our Model0sNote: Code change in upcoming videoEvaluating Our Model 20sEvaluating Our Model 30sFinding The Most Important Features0sReviewing The Project0s
-
Milestone Project 2: Supervised Learning (Time Series Data)Section Overview0sProject Overview0sDownloading the data for the next two projectsProject Environment Setup0sStep 1~4 Framework Setup0sExploring Our Data0sExploring Our Data 20sFeature Engineering0sTurning Data Into Numbers0sFilling Missing Numerical Values0sFilling Missing Categorical Values0sFitting A Machine Learning Model0sSplitting Data0sChallenge: What’s wrong with splitting data after filling it?Custom Evaluation Function0sReducing Data0sRandomizedSearchCV0sImproving Hyperparameters0sPreproccessing Our Data0sMaking Predictions0sFeature Importance0s
-
Data EngineeringData Engineering Introduction0sWhat Is Data?0sWhat Is A Data Engineer?0sWhat Is A Data Engineer 2?0sWhat Is A Data Engineer 3?0sWhat Is A Data Engineer 4?0sTypes Of Databases0sQuick Note: Upcoming VideoOptional: OLTP Databases0sOptional: Learn SQLHadoop, HDFS and MapReduce0sApache Spark and Apache Flink0sKafka and Stream Processing0s
-
Neural Networks: Deep Learning, Transfer Learning and TensorFlow 2Section Overview0sDeep Learning and Unstructured Data0sSetting Up With GoogleSetting Up Google Colab0sGoogle Colab Workspace0sUploading Project Data0sSetting Up Our Data0sSetting Up Our Data 20sImporting TensorFlow 20sOptional: TensorFlow 2.0 Default Issue0sUsing A GPU0sOptional: GPU and Google Colab0sOptional: Reloading Colab Notebook0sLoading Our Data Labels0sPreparing The Images0sTurning Data Labels Into Numbers0sCreating Our Own Validation Set0sPreprocess Images0sPreprocess Images 20sTurning Data Into Batches0sTurning Data Into Batches 20sVisualizing Our Data0sPreparing Our Inputs and Outputs0sOptional: How machines learn and what’s going on behind the scenes?Building A Deep Learning Model0sBuilding A Deep Learning Model 20sBuilding A Deep Learning Model 30sBuilding A Deep Learning Model 40sSummarizing Our Model0sEvaluating Our Model0sPreventing Overfitting0sTraining Your Deep Neural Network0sEvaluating Performance With TensorBoard0sMake And Transform Predictions0sTransform Predictions To Text0sVisualizing Model Predictions0sVisualizing And Evaluate Model Predictions 20sVisualizing And Evaluate Model Predictions 30sSaving And Loading A Trained Model0sTraining Model On Full Dataset0sMaking Predictions On Test Images0sSubmitting Model to Kaggle0sMaking Predictions On Our Images0sFinishing Dog Vision: Where to next?
-
Storytelling + Communication: How To Present Your Work
-
Career Advice + Extra BitsEndorsements On LinkedInQuick Note: Upcoming VideoWhat If I Don’t Have Enough Experience?0sLearning GuidelineQuick Note: Upcoming VideosJTS: Learn to Learn0sJTS: Start With Why0sQuick Note: Upcoming VideosCWD: Git + Github0sCWD: Git + Github 20sContributing To Open Source0sContributing To Open Source 20sExercise: Contribute To Open SourceCoding Challenges
-
Learn PythonWhat Is A Programming Language0sPython Interpreter0sHow To Run Python Code0sLatest Version Of Python0sOur First Python Program0sPython 2 vs Python 30sExercise: How Does Python Work?0sLearning Python0sPython Data Types0sHow To SucceedNumbers0sMath Functions0sDEVELOPER FUNDAMENTALS: I0sOperator Precedence0sExercise: Operator PrecedenceOptional: bin() and complex0sVariables0sExpressions vs Statements0sAugmented Assignment Operator0sStrings0sString Concatenation0sType Conversion0sEscape Sequences0sFormatted Strings0sString Indexes0sImmutability0sBuilt-In Functions + Methods0sBooleans0sExercise: Type Conversion0sDEVELOPER FUNDAMENTALS: II0sExercise: Password Checker0sLists0sList Slicing0sMatrix0sList Methods0sList Methods 20sList Methods 30sCommon List Patterns0sList Unpacking0sNone0sDictionaries0sDEVELOPER FUNDAMENTALS: III0sDictionary Keys0sDictionary Methods0sDictionary Methods 20sTuples0sTuples 20sSets0sSets 20s
-
Learn Python Part 2Breaking The Flow0sConditional Logic0sIndentation In Python0sTruthy vs Falsey0sTernary Operator0sShort Circuiting0sLogical Operators0sExercise: Logical Operators0sis vs ==0sFor Loops0sIterables0sExercise: Tricky Counter0srange()0senumerate()0sWhile Loops0sWhile Loops 20sbreak, continue, pass0sOur First GUI0sDEVELOPER FUNDAMENTALS: IV0sExercise: Find Duplicates0sFunctions0sParameters and Arguments0sDefault Parameters and Keyword Arguments0sreturn0sExercise: TeslaMethods vs Functions0sDocstrings0sClean Code0s*args and **kwargs0sExercise: Functions0sScope0sScope Rules0sglobal Keyword0snonlocal Keyword0sWhy Do We Need Scope?0sPure Functions0smap()0sfilter()0szip()0sreduce()0sList Comprehensions0sSet Comprehensions0sExercise: Comprehensions0sPython Exam: Testing Your UnderstandingModules in Python0sQuick Note: Upcoming VideosOptional: PyCharm0sPackages in Python0sDifferent Ways To Import0sNext StepsBonus Resource: Python Cheatsheet
-
Extra: Learn Advanced Statistics and Mathematics
-
Where To Go From Here?
-
BONUS SECTION
Become a complete A.I., Data Scientist and Machine Learning engineer! Join a live online community of 900,000+ engineers and a course taught by industry experts that have actually worked for large companies in places like Silicon Valley and Toronto. Graduates of Andrei’s courses are now working at Google, Tesla, Amazon, Apple, IBM, JP Morgan, Meta, + other top tech companies. You will go from zero to mastery!
Learn Data Science and Machine Learning from scratch, get hired, and have fun along the way with the most modern, up-to-date Data Science course on Udemy (we use the latest version of Python, Tensorflow 2.0 and other libraries). This course is focused on efficiency: never spend time on confusing, out of date, incomplete Machine Learning tutorials anymore. We are pretty confident that this is the most comprehensive and modern course you will find on the subject anywhere (bold statement, we know).
This comprehensive and project based course will introduce you to all of the modern skills of a Data Scientist and along the way, we will build many real world projects to add to your portfolio. You will get access to all the code, workbooks and templates (Jupyter Notebooks) on Github, so that you can put them on your portfolio right away! We believe this course solves the biggest challenge to entering the Data Science and Machine Learning field: having all the necessary resources in one place and learning the latest trends and on the job skills that employers want.
The curriculum is going to be very hands on as we walk you from start to finish of becoming a professional Machine Learning and Data Science engineer. The course covers 2 tracks. If you already know programming, you can dive right in and skip the section where we teach you Python from scratch. If you are completely new, we take you from the very beginning and actually teach you Python and how to use it in the real world for our projects. Don’t worry, once we go through the basics like Machine Learning 101 and Python, we then get going into advanced topics like Neural Networks, Deep Learning and Transfer Learning so you can get real life practice and be ready for the real world (We show you fully fledged Data Science and Machine Learning projects and give you programming Resources and Cheatsheets)!
The topics covered in this course are:
– Data Exploration and Visualizations
– Neural Networks and Deep Learning
– Model Evaluation and Analysis
– Python 3
– Tensorflow 2.0
– Numpy
– Scikit-Learn
– Data Science and Machine Learning Projects and Workflows
– Data Visualization in Python with MatPlotLib and Seaborn
– Transfer Learning
– Image recognition and classification
– Train/Test and cross validation
– Supervised Learning: Classification, Regression and Time Series
– Decision Trees and Random Forests
– Ensemble Learning
– Hyperparameter Tuning
– Using Pandas Data Frames to solve complex tasks
– Use Pandas to handle CSV Files
– Deep Learning / Neural Networks with TensorFlow 2.0 and Keras
– Using Kaggle and entering Machine Learning competitions
– How to present your findings and impress your boss
– How to clean and prepare your data for analysis
– K Nearest Neighbours
– Support Vector Machines
– Regression analysis (Linear Regression/Polynomial Regression)
– How Hadoop, Apache Spark, Kafka, and Apache Flink are used
– Setting up your environment with Conda, MiniConda, and Jupyter Notebooks
– Using GPUs with Google Colab
By the end of this course, you will be a complete Data Scientist that can get hired at large companies. We are going to use everything we learn in the course to build professional real world projects like Heart Disease Detection, Bulldozer Price Predictor, Dog Breed Image Classifier, and many more. By the end, you will have a stack of projects you have built that you can show off to others.
Here’s the truth: Most courses teach you Data Science and do just that. They show you how to get started. But the thing is, you don’t know where to go from there or how to build your own projects. Or they show you a lot of code and complex math on the screen, but they don’t really explain things well enough for you to go off on your own and solve real life machine learning problems.
Whether you are new to programming, or want to level up your Data Science skills, or are coming from a different industry, this course is for you. This course is not about making you just code along without understanding the principles so that when you are done with the course you don’t know what to do other than watch another tutorial. No! This course will push you and challenge you to go from an absolute beginner with no Data Science experience, to someone that can go off, forget about Daniel and Andrei, and build their own Data Science and Machine learning workflows.
Machine Learning has applications in Business Marketing and Finance, Healthcare, Cybersecurity, Retail, Transportation and Logistics, Agriculture, Internet of Things, Gaming and Entertainment, Patient Diagnosis, Fraud Detection, Anomaly Detection in Manufacturing, Government, Academia/Research, Recommendation Systems and so much more. The skills learned in this course are going to give you a lot of options for your career.
You hear statements like Artificial Neural Network, or Artificial Intelligence (AI), and by the end of this course, you will finally understand what these mean!
Click “Enroll Now” and join others in our community to get a leg up in the industry, and learn Data Scientist and Machine Learning. We guarantee this is better than any bootcamp or online course out there on the topic. See you inside the course!
Taught By:
Daniel Bourke:
A self-taught Machine Learning Engineer who lives on the internet with an uncurable desire to take long walks and fill up blank pages.
My experience in machine learning comes from working at one of Australia’s fastest-growing artificial intelligence agencies, Max Kelsen.
I’ve worked on machine learning and data problems across a wide range of industries including healthcare, eCommerce, finance, retail and more.
Two of my favourite projects include building a machine learning model to extract information from doctors notes for one of Australia’s leading medical research facilities, as well as building a natural language model to assess insurance claims for one of Australia’s largest insurance groups.
Due to the performance of the natural language model (a model which reads insurance claims and decides which party is at fault), the insurance company were able to reduce their daily assessment load by up to 2,500 claims.
My long-term goal is to combine my knowledge of machine learning and my background in nutrition to work towards answering the question “what should I eat?”.
Aside from building machine learning models on my own, I love writing about and making videos on the process. My articles and videos on machine learning on Medium, personal blog and YouTube have collectively received over 5-million views.
I love nothing more than a complicated topic explained in an entertaining and educative matter. I know what it’s like to try and learn a new topic, online and on your own. So I pour my soul into making sure my creations are accessible as possible.
My modus operandi (a fancy term for my way of doing things) is learning to create and creating to learn. If you know the Japanese word for this concept, please let me know.
Questions are always welcome.
Andrei Neagoie:
Andrei is the instructor of the highest rated Development courses on Udemy as well as one of the fastest growing. His graduates have moved on to work for some of the biggest tech companies around the world like Apple, Google, Amazon, JP Morgan, IBM, UNIQLO etc… He has been working as a senior software developer in Silicon Valley and Toronto for many years, and is now taking all that he has learned, to teach programming skills and to help you discover the amazing career opportunities that being a developer allows in life.
Having been a self taught programmer, he understands that there is an overwhelming number of online courses, tutorials and books that are overly verbose and inadequate at teaching proper skills. Most people feel paralyzed and don’t know where to start when learning a complex subject matter, or even worse, most people don’t have $20,000 to spend on a coding bootcamp. Programming skills should be affordable and open to all. An education material should teach real life skills that are current and they should not waste a student’s valuable time. Having learned important lessons from working for Fortune 500 companies, tech startups, to even founding his own business, he is now dedicating 100% of his time to teaching others valuable software development skills in order to take control of their life and work in an exciting industry with infinite possibilities.
Andrei promises you that there are no other courses out there as comprehensive and as well explained. He believes that in order to learn anything of value, you need to start with the foundation and develop the roots of the tree. Only from there will you be able to learn concepts and specific skills(leaves) that connect to the foundation. Learning becomes exponential when structured in this way.
Taking his experience in educational psychology and coding, Andrei’s courses will take you on an understanding of complex subjects that you never thought would be possible.
See you inside the course!
What's included
- 43.5 hours on-demand video
- 1 coding exercise
- 60 articles
- 14 downloadable resources
- Access on mobile and TV
- Certificate of completion