Sunteți pe pagina 1din 22

learn data science by building

SYLLABUS
20
WORKSHOPS
620
PARTICIPANTS
20+
CORPORATE CLIENTS
US
WHY US?
Curriculum tailored to the needs of industries

Small cohort sizes allow more personal interaction


with teaching assistants

Final projects are directly applicable to the industry


SPECIALIZATION DETAILS :
A fun, hands-on, and project-based
learn data science by building
specialization that helps student gain full
proficiency in data visualization systems
and tools. Create compelling narratives by
combining charting elements with custom
aesthetics under the guidance of our
instructors.

The learn-by-building module in all the


workshops follows our project-based
learning philosophy to this specialization.
The course capstone requires that the
student build a real-world application
under stringent criteria modeled after
real business scenarios.
Programming for Data Science
Programming for Data Science is a course that Upon completion of this workshop, you will be
covers the important programming paradigms and familiar with the programming language, popular
tools used by data analysts and data scientists tools, libraries (data science packages) and tool kits
today. You will be guided through a series of coding required to excel in your data analysis and statistical
exercises designed to maximize your familiarity with computing projects.
data science programming in RStudio, an integrated
development environment for the statistical
computing language R.

Workshop Module 1: Workshop Module 2: Academy Modules


Data Science in R Data Manipulation Graded Quiz
Data Science in R Data Manipulation II Working with R
R Programming Basics Vector Types and Classes R Scripts and Functions
Why Learn R? List and Objects R Markdown
R Studio Interface Matrix and Data Frames Why Care About Reproducibility
Data Structures in R
Practical Data Cleansing Learning-by-Building Module (2 Points)
Working with Data The Data Transformation Process
Understanding Statistics Reproducible Data Science Projects Retail Sales Pre-Diagnostic Cleanup Script
Reading & Extracting Data Reading and Writing from your IDE Build a programming script that reads data into your
Exploratory Data Analysis workspace, perform various data cleansing tasks, and
R in Practice save the result in the appropriate formats for data
Programming Exercise: e-Commerce Retail Datasets science work
Data Manipulation
In-depth Review of Data Frame Subsetting
Working with Your Global Environment Reproducible Data Science
Sampling and Randomization
Getting Familiar with Your Workspace Create an R Markdown file that combines data
Cross-Tabulations
Continuous and Categorical Data transformation code with explanatory text. Add
Aggregations
formatting styles and hierarchical structure using
Markdown.
Practical Statistics
Pave the statistical foundation for more advanced The 6-hour course is optional for participations of
machine learning theories later on in the the Data Visualization and Machine Learning
specialization by picking up the key ideas in Specialization and intended for learners without
statistical thinking. Learn to interpret correlations, prior experience in statistics.
construct confidence intervals and other statistical
principles that form the basis of many common
machine learning models.

Workshop Module 1: Workshop Module 2: Academy Modules


Descriptive Statistics Inferential Statistics Tips & Techniques: R for Statisticians
5-Number Summary Probabilities Density Plots
Mean, Median, Mode Probability Mass Function Interpreting Box Plots (Box-and-Whisker)
Measures of Central Tendency Probability Density Function Better Summary Statistics with skimr()
Quantiles in R Expected Values Pais Matrix

Central Tendency Intervals Learning-by-Building Module (Not Graded)


& Variability Confidence Intervals
Probability Distribution Function Prediction Intervals Statistical Treatment of Retail Dataset
Visualizing Central Tendency p-Values Using what you’ve learned, formulate a question and
Variation, Variance and Covariance derive a statistical hypothesis test to answer the question.
Inferential Statistics in Practice You have to demonstrate that you’re able to make
Standard Score & z-Score Hypothesis Testing decisions using data in a scientific manner.
Standard Normal Curve Deriving Scientific Truths from Data Examples of questions can be:
Central Limit Theorem Case Study Is there a difference in profitability between standard
z-Score Calculation & Student's T-test shipment and same-day shipment?
Supposed there is no difference in profitability
between the different product segment, what is the
probability that we obtain the current observation due
to pure chance alone?
Data Visualization in R
A fun, hands-on, and project-based workshop that The 12-hour course follows our learn-by-building
help students gain full proficiency in data approach, in that students are tasked to reproduce a
visualization systems and tools. Create compelling series of plots applying what they’ve learned. While it
narratives by combining charting elements with covers the three main plotting systems in R, its
custom aesthetics under the guidance of our particular focus is on ggplot2 and the additional
instructors. libraries centered around it that bring interactivity
and enhanced aesthetic options to the art of
creating rich, powerful visualizations.

Workshop Module 1: Workshop Module 2:


Plotting Essentials Richer Visualization Techniques Academy Modules
Base Plotting I Enhancing ggplot2 II Project: Mining Trending Videos on YouTube
Plots and Lines Flipping Coordinates and Axis Rotation Hands-on Data Visualization
Built-in Plot Types Multi-dimensional Faceting Identifying Temporal Patterns in Trending Videos
Legends and Annotations Text Layers and Label Layers Combining Aesthetics and Geometries
Other Built-in Plotting Functionalities Expected Values
Base Plotting II Enhancing ggplot2 III Learning-by-Building Module (2 Points)
Histograms and Curves Enriching: Scatterplots and Bubble Plots
Cleveland's Dot Plot Enriching: Jitterplots Creating a Publication-Grade Plot
Axis, Titles, Subtitles and Panel Styles Enriching: Boxplots and Violin Plots Applying what you’ve learned, create an economics- or
The Notorious Pie Chart Layer Transparency social-related plot that is polished with the appropriate
annotations, aesthetics, and some simple commentary.
Working with ggplot2 You may use the same "YouTube Trending Videos" dataset
Enhancing ggplot2 IV
Grammar of Graphics System or any other dataset for this practice.
Enriching: Column Plots
Mapping Aesthetics Enriching: Texts and Labels Creating an Interactive Map
Working with Geometries Enriching: Horizontal and Vertical Lines Applying what you’ve learned, create a web page with an
Background Image Fills and Colors interactive map embedded on it. Use a custom icon for the
map markers to represent business locations, and show
Enhancing ggplot2 Other Visualization Toolset details about each location pin (“markers”) upon user’s
Axis, Titles and Scales Discrete, Continuous, and Gradient Colors interaction with it.
Adding Themes to Your Plots Facet with Wraps and Grids
Custom Aesthetics and Styles Visualizing Spatial Data
Working with Legends Working with Leaflet and Maps
Interactive Plotting & Web Dashboard
Building on the foundation from previous classes, we The 12-hour course follows our learn-by-building
will create a series of interactive plots and gadgets approach, in that students are tasked to reproduce a
that renders multiple visualization elements based series of plots applying what they’ve learned. It
on user’s input. This is the final workshop leading up covers an exhaustive list of techniques that add
to the data visualization capstone project. interactivity to an R document and set the stage for
the data science capstone project.

Workshop Module 1: Workshop Module 2: Academy Modules


Interactive Visualization Web Dashboard Development Tips on Web Dashboard Deployment
Working with Plotly Flex Dashboard Working with Live Data
Refresher on dplyr Creating Flex Dashboard from RStudio App Deployment Solutions
ggplotly Function Layouts Tips for Live Dashboard Performance
Visualization as a HTML Widget Hands-on Practice: Text, Plots, Tables
Range Slider and Other Interactivity Demonstration and Practical Advice
Learning-by-Building Module (4 Points)
Publication & Layout Options Interactive Document
Multiple Plots Arrangement Inputs and Outputs Building an Interactive Dashboard
More Export Functions The renderPlot() Function Applying what you’ve learned, create a paginated web
Subplots Embedded Application dashboard with a rich set of UI elements coupled with
Tips and Techniques for Layouts Demonstration and Practical Advice the appropriate server logic. The web dashboard can be
of any theme, using any dataset, but must feature an
Shiny Web App input panel that accepts end user inputs and render the
Shiny Dashboard output accordingly.
Tabs and Pagination
UI, Server and Shiny Functions
Custom Styles, Structure
SPECIALIZATION DETAILS :
An intensive specialization that strives for
learn data science by building
a fine balance between practical applications
and mathematical rigor in teaching essential
machine learning concepts. By taking a learn-
by-building approach, you will learn to develop
regression and classification algorithms and
incorporate them into real-life solutions or
data products / business applications.

The modules in all the workshops follow our


project-based learning philosophy to this
specialization. The course capstone requires
that the student build a real-world application
under stringent criteria modeled after real
business scenarios.
Programming for Data Science
Programming for Data Science is a course that Upon completion of this workshop, you will be
covers the important programming paradigms and familiar with the programming language, popular
tools used by data analysts and data scientists tools, libraries (data science packages) and tool kits
today. You will be guided through a series of coding required to excel in your data analysis and statistical
exercises designed to maximize your familiarity with computing projects.
data science programming in RStudio, an integrated
development environment for the statistical
computing language R.

Workshop Module 1: Workshop Module 2: Academy Modules


Data Science in R Data Manipulation Graded Quiz
Data Science in R Data Manipulation II Working with R
R Programming Basics Vector Types and Classes R Scripts and Functions
Why Learn R? List and Objects R Markdown
R Studio Interface Matrix and Data Frames Why Care About Reproducibility
Data Structures in R
Practical Data Cleansing Learning-by-Building Module (2 Points)
Working with Data The Data Transformation Process
Understanding Statistics Reproducible Data Science Projects Retail Sales Pre-Diagnostic Cleanup Script
Reading & Extracting Data Reading and Writing from your IDE Build a programming script that reads data into your
Exploratory Data Analysis workspace, perform various data cleansing tasks, and
R in Practice save the result in the appropriate formats for data
Programming Exercise: e-Commerce Retail Datasets science work
Data Manipulation
In-depth Review of Data Frame Subsetting
Working with Your Global Environment Reproducible Data Science
Sampling and Randomization
Getting Familiar with Your Workspace Create an R Markdown file that combines data
Cross-Tabulations
Continuous and Categorical Data transformation code with explanatory text. Add
Aggregations
formatting styles and hierarchical structure using
Markdown.
Practical Statistics
Pave the statistical foundation for more advanced The 6-hour course is optional for participations of
machine learning theories later on in the the Data Visualization and Machine Learning
specialization by picking up the key ideas in Specialization and intended for learners without
statistical thinking. Learn to interpret correlations, prior experience in statistics.
construct confidence intervals and other statistical
principles that form the basis of many common
machine learning models.

Workshop Module 1: Workshop Module 2: Academy Modules


Descriptive Statistics Inferential Statistics Tips & Techniques: R for Statisticians
5-Number Summary Probabilities Density Plots
Mean, Median, Mode Probability Mass Function Interpreting Box Plots (Box-and-Whisker)
Measures of Central Tendency Probability Density Function Better Summary Statistics with skimr()
Quantiles in R Expected Values Pais Matrix

Central Tendency Intervals Learning-by-Building Module (Not Graded)


& Variability Confidence Intervals
Probability Distribution Function Prediction Intervals Statistical Treatment of Retail Dataset
Visualizing Central Tendency p-Values Using what you’ve learned, formulate a question and
Variation, Variance and Covariance derive a statistical hypothesis test to answer the question.
Inferential Statistics in Practice You have to demonstrate that you’re able to make
Standard Score & z-Score Hypothesis Testing decisions using data in a scientific manner.
Standard Normal Curve Deriving Scientific Truths from Data Examples of questions can be:
Central Limit Theorem Case Study Is there a difference in profitability between standard
z-Score Calculation & Student's T-test shipment and same-day shipment?
Supposed there is no difference in profitability
between the different product segment, what is the
probability that we obtain the current observation due
to pure chance alone?
Regression Models
This course strives for a fine balance between We strongly recommend that you complete Practical
business applications and mathematical rigor in its Statistics prior to taking this course. Upon completion
treatment to regression models, one of the most of this workshop, you will acquire a rigorous statistical
essential statistical techniques in the field of understanding of machine learning models, allowing
machine learning. Its aim is to equip you with the you to extrapolate the same ideas into other, more
knowledge to investigate relationships between advanced machine learning models.
variables of data effectively and rigorously.

Workshop Module 1: Workshop Module 2: Academy Modules


Regression Models I Regression Models II Graded Quiz
OLS Regression Interpreting Linear Models
Understanding Least Squares Estimates and Standard Errors
Learning-by-Building Module (3 Points)
Outliers I t-Value and p-Value Recommendation on Lowering Crime Rates
Simple Linear Regression Adjusted R-Squared Write a regression analysis report applying what you’ve
learned in the workshop. Using the dataset provided by
Linear Models in R Multiple Regression you, write your findings on the different socioeconomic
Understanding Coefficients Multicollinearity and VIF
variables most highly correlated to crime rates.
Plotting Regression Model Assumptions
Model Construction Bias-Variance Trade-off
Explain your recommendations where appropriate.
Outliers II: Leverage and Influence
Interpreting Linear Models
Residuals Manually Dive Deeper: Regression Models
Coefficients Manually Model Selection and Specification
R-Squared Manually Step-wise Regression
All-possible Regressions
Residual Plots
Model Diagnostics
Limitations of Regression Models
Classification in Machine Learning 1
Learn to solve binary and multi-class classification We strongly recommend that you complete the
models using machine learning algorithms that are Regression Models workshop prior to taking this
easily understood and readily interpretable. You will course. Upon completion of this workshop, you will
learn to write a classification algorithm from scratch, acquire the depth to develop, apply, and evaluate two
and appreciate the mathematical foundations highly versatile algorithms widely used today.
underpinning logistic regressions and nearest
neighbors algorithms.

Workshop Module 1: Workshop Module 2:


Logistic Regression Nearest Neighbours Algorithm
Relating Probabilities to Odds Closer Look at Classification
Understanding Odds Probabilities vs Class Response
Understanding Log of Odds Confusion Matrix
Plotting Odds and Log of Odds Sensitivity, Specificity & Precision

Logistic Regression from First Principles k-NN in Action


Sigmoidal Logistic Function Characteristics of k-NN
Key Assumptions of Sigmoid Function Positives and Negatives
Extra Proof: Intuition Behind The Sigmoid Function Diagnosing Breast Cancer with k-NN

Logistic Regression in Action Building Blocks of k-NN


Binary Logistic Regression Distance Function (Euclidean, Minkowsky)
Interpreting Coefficients The k Parameter
Interpretation Against Continuous & Discrete Variables Standardization vs Min-Max Normalization

Practical Tips and Case Study k-NN from First Principles


Flight Delay Prediction Examples Classifying Customer Segments with k-NN
Customer Churn and Attrition Examples Writing Your Own k-NN Classifier
Risk Modeling on Loans from Quarter 4, 2017 Predicting Using Your Own k-NN Classifier
Performance Evaluation and Model Selection
AIC (Akaike Information Criteria)
Null Deviance and Residual Deviance
Hauck Donner Effect
Classification in Machine Learning 2
Learn to apply the law of probabilities, boosting, We strongly recommend that you complete the
bootstrap aggregation, k-fold cross validation, Classification in Machine Learning 1 workshop prior
ensembling methods, and a variety of other to taking this course. Some concepts presented
techniques as we build some of the most widely throughout the lecture may be less-than-ideal for
used machine learning algorithms today. Learn to practitioners who have not completed the
add performance to your models using pre-requisite courses.
mathematically sound principles you’ll learn in this
course.

Workshop Module 1: Workshop Module 2:


Naive Bayes Tree-Based Methods and Ensembles
Law of Probability Decision Trees
Dependent and Independent Events Advantages and Model Characteristics
Bayes Theorem Information Gain and Splitting Criterion
Formula for Posterior Probability Pruning and Tree Size

Naive Bayes Classifier Decision Trees in Action


Characteristics of a Naive Bayes Classifier Predicting Diabetes from Diagnostics Measurement
The "Naive" Assumptions AUC Curve
Customer Churn Example Key Considerations and Practical Advice

Practical and Performance Considerations Machine Learning Theories


The Case for Smoothing Logistic Regression, Naive Bayes and Decision Trees
Laplace (Add-One) Have More in Common Than You Think
Thinking about Training vs Prediction Speed Industrial Applications
Thinking About Decision Boundaries
Naive Bayes in Action
Spam Classification High-Performance Machine Learning
Predicting on Text (Corpus) Bias-Variance Tradeoff Revisited k-Fold Cross Validation
Predicting Political Party Affiliation Predicting Exercise Form with Fitness Tracker Data
Classification in Machine Learning 1
Learn to solve binary and multi-class classification We strongly recommend that you complete the
models using machine learning algorithms that are Regression Models workshop prior to taking this
easily understood and readily interpretable. You will course. Upon completion of this workshop, you will
learn to write a classification algorithm from scratch, acquire the depth to develop, apply, and evaluate two
and appreciate the mathematical foundations highly versatile algorithms widely used today.
underpinning logistic regressions and nearest
neighbors algorithms.

Academy Modules
Graded Quiz

Learning-by-Building Module (3 points)


Logistic Regression on Credit Risk Customer Segment Prediction
Applying what you’ve learned, present a simple R Markdown Applying what you’ve learned, present a simple R Markdown document
document in which you demonstrate the use of logistic regression on in which you demonstrate the use of knn on the wholesale.csv dataset.
the lbb_loans.csv dataset. Explain your findings wherever necessary and Compare the k-NN to the logistic regression model and answer the
show the necessary data preparation steps. To help you through the following questions throughout the document:
exercise, consider the following questions throughout the document:
What is your accuracy? Was the logistic regression better than kNN in
How do we correctly interpret the negative coefficients obtained from terms of accuracy? (recall the lesson on obtaining an unbiased estimate
your logistic regression? of the model’s accuracy)
How do we know which of the variables are more statistically significant Was the logistic regression better than our kNN model at explaining
as predictors? which of the variables are good predictors of a customer’s industry?
What are some strategies to improve your model? List down 1 disadvantage and 1 strength of each of the approach (kNN
and logistic regression)
Classification in Machine Learning 2
Learn to apply the law of probabilities, boosting, We strongly recommend that you complete the
bootstrap aggregation, k-fold cross validation, Classification in Machine Learning 1 workshop prior
ensembling methods, and a variety of other to taking this course. Some concepts presented
techniques as we build some of the most widely throughout the lecture may be less-than-ideal for
used machine learning algorithms today. Learn to practitioners who have not completed the
add performance to your models using pre-requisite courses.
mathematically sound principles you’ll learn in this
course.

Academy Modules
Graded Quiz

Learning-by-Building Module (3 Points)


Identifying Risky Bank Loans
Use any of the 3 classification algorithms you’ve learned
in this lesson to predict the risk status of a bank loan.
The variable default in the dataset indicates whether the
applicant did default on the loan issued by the bank.

Use an R Markdown document to lay out your process,


and explain the methodology in 1 or 2 brief paragraph.
The student should be awarded the full (3) points when:
The preprocessing steps are done, and the student
show an understanding of holding out a test/cross -
validation set for an estimate of the model’s
performance on unseen data
The model’s performance is sufficiently explained
(accuracy may not be the most helpful metric here!
Recall about what you’ve learned regarding specificity
and sensitivity)
The student demonstrated extra effort in evaluating
his/her model, and proposes ways to improve the
accuracy obtained from the initial model
Unsupervised Machine Learning
Learn PCA (Principal Component Analysis), We strongly recommend that you complete the
Clustering, and other algorithms to work with pre-requisite courses prior to taking this course.
unsupervised machine learning tasks where the Some concepts presented throughout the lecture
target variable is not known or defined. Applying may be less-than-ideal for practitioners who are new
what you’ll learn from this workshop, you will be to the field of machine learning.
tasked to develop an anomaly detection or an
e-commerce product recommendation model that
can be related to real-life business scenarios.

Workshop Module 1: Workshop Module 2: Academy Modules


Dimensionality Reduction k-Means Clustering Graded Quiz
Background Understanding Clustering
Understanding Unsupervised Learning Centroid-based Clustering Algorithms Learning-by-Building Module (3 Points)
The "Dimensionality" Problem The k-Means Procedure
Industrial Use of PCA Mathematical Details Diving into Wholesale Transactions
Principal Component Analysis Using any of the two unsupervised learning algorithms
Rethinking About Covariances k-Means Clustering in Action you’ve learned, produce a simple R markdown document
The Case for PCA Cluster-based Product Recommendation where you demonstrate an exercise of either clustering or
Eigenvalues and Eigenvectors Scaling and Implementation Details dimensionality reduction on the wholesale.csv data
Visualizing Clusters provided to you
PCA from First Principles
Just Enough Matrix Algebra Evaluating k-Means Digging Deep into NYC Property Sales
Mathematical Proof Between Sum-of-squares Using any of the two unsupervised learning algorithms
Visualization and Visual Proof Within Sum-of-squares you’ve learned, produce a simple R markdown document
Combining k-Means with PCA where you demonstrate an exercise of either clustering or
PCA in Action dimensionality reduction on the nyc data provided to you
Dubious Property Sales in NYC
PCA on US Arrests Data Explain your choice of parameters (how you choose k for
Biplot and The Variables Factor Map k-means clustering, or how you choose to retain n number
of dimensions for PCA) from the original data. What are
PCA in Action II some business utilities for the unsupervised model you’ve
Eigenfaces developed? The R Markdown document should be no
PCA on Credit Loan Data longer than 4 paragraph, and contain one or two
Deconstruction and Reconstructing Faces with PCA visualizations.
Principal Components by Hand
Time Series And Forecasting
Decomposition of time series allows us to learn We strongly recommend that you complete the
about the underlying seasonality, trend and random pre-requisite workshops prior to taking this course.
fluctuations in a systematic fashion. In this Some concepts presented throughout the lecture
workshop, we learn the methods to account for may be less-than-ideal for practitioners who have
seasonality and trend, work with autocorrelation not completed the pre-requisite courses.
models and create industry-scale forecasts using
modern tools and frameworks.

Workshop Module 1: Workshop Module 2: Academy Modules


Time Series I Forecasting Graded Quiz
Working with Time Series Forecasting I
Application of Time Series Simple Moving Average Learning-by-Building Module (3 points)
Definition of a ts Object Simple Moving Average from First Principles
Forecasting the Crime rate in Chicago
Functions to Work with Time Series Log-Transformation
Download the dataset from Chicago Crime Portal, and use
Time Series in Action Forecasting II a sample of these data to build a forecasting project where
Indonesia's Gas Emissions, 1970-2012 Forecasting Using One-sided SMA you inspect the seasonality and trend of crime in Chicago.
Frequency, Start and End Forecasting Using Exponential Smoothing Submit you project in the form of a RMD format, and address
Time Series Plots Holt's Exponential Smoothing the following question:

Classical Decomposition Forecasting III Is crime generally rising in Chicago in the past decade
Trend, Seasonality and Residuals The beta and gamma Coefficients (last 10 years)?
Understanding Lags Mathematical Details Is there a seasonal component to the crime rate?
Additive vs Multiplicative Holt-Winters Exponential Smoothing Which time series method seems to capture the variation
in your time series better? Explain your choice of algorithm
Classical Decomposition in Action Advanced Time Series and its key assumptions
ACF and PACF
Monthly Airline Passenger, 1949-1960
ARMA and ARIMA Models Student should awarded the full (3) points if they address at l
The decompose Function
Stationarity and Differencing east 2 of the above questions.
Understanding Smoothing
Advanced Time Series II
Techniques to Work with Time Series Augmented Dickey-Fuller (ADF) Test
Adjusting for Seasonality Seasonal ARIMA
Detrending Tips to Work With xts
Decomposing Non-Seasonal Time Series Facebook's Prophet
Quantmod for Quantitative Traders
Neural Network & Deep Learning
Develop artificial neural networks that can recognize We strongly recommend that you complete the
face, handwriting patterns and are at the core of pre-requisite workshops prior to taking this course.
some of the most cutting-edge cognitive models in Some concepts presented throughout the lecture
the AI landscape. We will learn to create a may be less-than-ideal for practitioners who have
backpropagation neural network from scratch, and not completed the pre-requisite courses.
use our neural network for classification tasks. This
class is the final course in the Machine Learning
Specialization.

Workshop Module 1: Workshop Module 2:


Neural Network Deep Learning
Artificial Neural Networks Neural Networks from First Principles MXNet in Action
The Biological Brain Inspiration Sum of Squared Errors Thinking About Parallelism
Cost Function Cross-Entropy Error MNIST Handwritten Digit Recognition
The Building Blocks of Neural Networks The Gradient Descent Algorithm Predictions with MXNet and Practical Advice
Neural Network Architecture Neural Networks from Scratch
Layers, Nodes and Signals Gradient Descent by Hand
Network Topology Neural Network by Hand Academy Modules
Direction of Signal Learning Rate and Implementation Details Graded Quiz
Neural Network Architecture II Neural Networks in Action
Hidden Layers Putting It All Together Learning-by-Building Module (3 Points)
Computing with Neural Network Parameterization and Practical Advice
Mathematical Details Deep Learning for Classification and Regression Image Classification Using Neural Network
Build a neural network capable of classifying images into
Multi-Layer Perceptrons (MLP) Deep Learning in Action one of many classes and explain the choice of your
Backpropagation of Error Theorizing with Effect of Depth architecture. Test your neural network using unseen
Feed-forward vs Recurrent Activation Functions images – can your algorithm correctly classify 80%
Mathematical Details Visualizing Logarithmic Loss of the images?

Deep Learning in Action II


Predicting Bank Telemarketing Campaign
Visualizing Tricks for Deep Neural Networks
Parameterization and Practical Advice
learn data science by building IDR 14.000.000 learn data science by building

IDR 26.000.000

FULL TR ACK

learn data science by building

learn data science by building

IDR 35.000.000

S-ar putea să vă placă și