Tag: Deep Learning

Duration

21 hours (usually 3 days including breaks)

Requirements

• Programming experience in any language.
• A general familiarity with C/C++ helps.
• An interest in Artificial Intelligence (AI).

Audience

• Software developers and programmers wishing to enable Machine and Deep Learning within their applications

Overview

Torch is an open source machine learning library and a scientific computing framework based on the Lua programming language. It provides a development environment for numerics, machine learning, and computer vision, with a particular emphasis on deep learning and convolutional nets. It is one of the fastest and most flexible frameworks for Machine and Deep Learning and is used by companies such as Facebook, Google, Twitter, NVIDIA, AMD, Intel, and many others.

In this instructor-led, live training, we cover the principles of Torch, its unique features, and how it can be applied in real-world applications. We step through numerous hands-on exercises all throughout, demonstrating and practicing the concepts learned.

By the end of the course, participants will have a thorough understanding of Torch’s underlying features and capabilities as well as its role and contribution within the AI space compared to other frameworks and libraries. Participants will have also received the necessary practice to implement Torch in their own projects.

Format of the Course

• Overview of Machine and Deep Learning
• In-class coding and integration exercises
• Test questions sprinkled along the way to check understanding

Course Outline

Introduction to Torch

• Like NumPy but with CPU and GPU implementation
• Torch’s usage in machine learning, computer vision, signal processing, parallel processing, image, video, audio and networking

Installing Torch

• Linux, Windows, Mac
• Bitmapi and Docker

Installing Torch Packages

• Using the LuaRocks package manager

Choosing an IDE for Torch

• ZeroBrane Studio
• Eclipse plugin for Lua

Working with the Lua Scripting Language and LuaJIT

• Lua’s integration with C/C++
• Lua syntax: datatypes, loops and conditionals, functions, functions, tables, and file i/o.
• Object orientation and serialization in Torch
• Coding exercise

Loading a Dataset in Torch

• MNIST
• CIFAR-10, CIFAR-100
• Imagenet

Machine Learning in Torch

• Deep Learning
  • Manual feature extraction vs convolutional networks
• Supervised and Unsupervised Learning
  • Building a neural network with Torch
• N-dimensional arrays

Image Analysis with Torch

• Image package
• The Tensor library

Working with the REPL Interpreter

Working with Databases

Networking and Torch

GPU Support in Torch

Integrating Torch

• C, Python, and others

Embedding Torch

• iOS and Android

Other Frameworks and Libraries

• Facebook’s optimized deep-learning modules and containers

Creating Your Own Package

Testing and Debugging

Releasing Your Application

The Future of AI and Torch

Summary and Conclusion

Duration

21 hours (usually 3 days including breaks)

Requirements

• Java

Overview

Deeplearning4j is an Open-Source Deep-Learning Software for Java and Scala on Hadoop and Spark.

Audience

This course is meant for engineers and developers seeking to utilize DeepLearning4J in their image recognition projects.

Course Outline

Getting Started

• Quickstart: Running Examples and DL4J in Your Projects
• Comprehensive Setup Guide

Convolutional Neural Networks 

• Convolutional Net Introduction
• Images Are 4-D Tensors?
• ConvNet Definition
• How Convolutional Nets Work
• Maxpooling/Downsampling
• DL4J Code Sample
• Other Resources

Datasets

• Datasets and Machine Learning
• Custom Datasets
• CSV Data Uploads

Scaleout

• Iterative Reduce Defined
• Multiprocessor / Clustering
• Running Worker Nodes

Advanced DL2J

• Build Locally From Master
• Use the Maven Build Tool
• Vectorize Data With Canova
• Build a Data Pipeline
• Run Benchmarks
• Configure DL4J in Ivy, Gradle, SBT etc
• Find a DL4J Class or Method
• Save and Load Models
• Interpret Neural Net Output
• Visualize Data with t-SNE
• Swap CPUs for GPUs
• Customize an Image Pipeline
• Perform Regression With Neural Nets
• Troubleshoot Training & Select Network Hyperparameters
• Visualize, Monitor and Debug Network Learning
• Speed Up Spark With Native Binaries
• Build a Recommendation Engine With DL4J
• Use Recurrent Networks in DL4J
• Build Complex Network Architectures with Computation Graph
• Train Networks using Early Stopping
• Download Snapshots With Maven
• Customize a Loss Function

Duration

21 hours (usually 3 days including breaks)

Requirements

• Programming experience in Python.
• Experience with the Linux command line.

Audience

• Developers
• Data Scientists

Overview

TensorFlow is a popular machine learning library developed by Google for deep learning, numeric computation, and large-scale machine learning. TensorFlow 2.0, released in Jan 2019, is the newest version of TensorFlow and includes improvements in eager execution, compatibility and API consistency.

This instructor-led, live training (online or onsite) is aimed at developers and data scientists who wish to use Tensorflow 2.x to build predictors, classifiers, generative models, neural networks and so on.

By the end of this training, participants will be able to:

• Install and configure TensorFlow 2.x.
• Understand the benefits of TensorFlow 2.x over previous versions.
• Build deep learning models.
• Implement an advanced image classifier.
• Deploy a deep learning model to the cloud, mobile and IoT devices.

Format of the Course

• Interactive lecture and discussion.
• Lots of exercises and practice.
• Hands-on implementation in a live-lab environment.

Course Customization Options

• To request a customized training for this course, please contact us to arrange.
• To learn more about TensorFlow, please visit: https://www.tensorflow.org/

Course Outline

Introduction

• TensorFlow 2.x vs previous versions — What’s new

Setting up Tensoflow 2.x

Overview of TensorFlow 2.x Features and Architecture

How Neural Networks Work

Using TensorFlow 2.x to Create Deep Learning Models

Analyzing Data

Preprocessing Data

Building a Model

Implementing a State-of-the-Art Image Classifier

Training the Model

Training on a GPU vs a TPU

Evaluating the Model

Making Predictions

Evaluating the Predictions

Debugging the Model

Saving a Model

Deploying a Model to the Cloud

Deploying a Model to a Mobile Device

Deploying a Model to an Embedded System (IoT)

Integrating a Model with Different Languages

Troubleshooting

Summary and Conclusion

Duration

28 hours (usually 4 days including breaks)

Requirements

• An understanding of Python programming
• An understanding of Python libraries in general

Audience

• Programmers with interest in linguistics
• Programmers who seek an understanding of NLP (Natural Language Processing) 

Overview

DL (Deep Learning) is a subset of ML (Machine Learning).

Python is a popular programming language that contains libraries for Deep Learning for NLP.

Deep Learning for NLP (Natural Language Processing) allows a machine to learn simple to complex language processing. Among the tasks currently possible are language translation and caption generation for photos.

In this instructor-led, live training, participants will learn to use Python libraries for NLP as they create an application that processes a set of pictures and generates captions. 

By the end of this training, participants will be able to:

• Design and code DL for NLP using Python libraries.
• Create Python code that reads a substantially huge collection of pictures and generates keywords.
• Create Python Code that generates captions from the detected keywords.

Format of the course

• Part lecture, part discussion, exercises and heavy hands-on practice

Course Outline

Introduction to Deep Learning for NLP

Differentiating between the various types of  DL models

Using pre-trained vs trained models

Using word embeddings and sentiment analysis to extract meaning from text 

How Unsupervised Deep Learning works

Installing and Setting Up Python Deep Learning libraries

Using the Keras DL library on top of TensorFlow to allow Python to create captions

Working with Theano (numerical computation library) and TensorFlow (general and linguistics library) to use as extended DL libraries for the purpose of creating captions. 

Using Keras on top of TensorFlow or Theano to quickly experiment on Deep Learning

Creating a simple Deep Learning application in TensorFlow to add captions to a collection of pictures

Troubleshooting

A word on other (specialized) DL frameworks

Deploying your DL application

Using GPUs to accelerate DL

Closing remarks

Duration

21 hours (usually 3 days including breaks)

Requirements

• Statistics
• Python
• (optional) A laptop with NVIDIA GPU that supports CUDA 8.0 and cuDNN 5.1, with 64-bit Linux installed

Overview

TensorFlow is a 2nd Generation API of Google’s open source software library for Deep Learning. The system is designed to facilitate research in machine learning, and to make it quick and easy to transition from research prototype to production system.

Audience

This course is intended for engineers seeking to use TensorFlow for their Deep Learning projects

After completing this course, delegates will:

• understand TensorFlow’s structure and deployment mechanisms
• be able to carry out installation / production environment / architecture tasks and configuration
• be able to assess code quality, perform debugging, monitoring
• be able to implement advanced production like training models, building graphs and logging

Course Outline

Machine Learning and Recursive Neural Networks (RNN) basics

• NN and RNN
• Backprogation
• Long short-term memory (LSTM)

TensorFlow Basics

• Creation, Initializing, Saving, and Restoring TensorFlow variables
• Feeding, Reading and Preloading TensorFlow Data
• How to use TensorFlow infrastructure to train models at scale
• Visualizing and Evaluating models with TensorBoard

TensorFlow Mechanics 101

• Prepare the Data
  • Download
  • Inputs and Placeholders
• Build the Graph
  • Inference
  • Loss
  • Training
• Train the Model
  • The Graph
  • The Session
  • Train Loop
• Evaluate the Model
  • Build the Eval Graph
  • Eval Output

Advanced Usage

• Threading and Queues
• Distributed TensorFlow
• Writing Documentation and Sharing your Model
• Customizing Data Readers
• Using GPUs¹
• Manipulating TensorFlow Model Files

TensorFlow Serving

• Introduction
• Basic Serving Tutorial
• Advanced Serving Tutorial
• Serving Inception Model Tutorial

¹ The Advanced Usage topic, “Using GPUs”, is not available as a part of a remote course. This module can be delivered during classroom-based courses, but only by prior agreement, and only if both the trainer and all participants have laptops with supported NVIDIA GPUs, with 64-bit Linux installed (not provided by NobleProg). NobleProg cannot guarantee the availability of trainers with the required hardware.

Duration

14 hours (usually 2 days including breaks)

Requirements

• Experience in the medical industry
• No programming experience is required

Overview

Machine Learning is a branch of Artificial Intelligence wherein computers have the ability to learn without being explicitly programmed. Deep Learning is a subfield of Machine Learning which attempts to mimic the workings of the human brain in making decisions. It is trained with data in order to automatically provide solutions to problems. Deep Learning provides vast opportunities for the medical industry which is sitting on a data goldmine.

In this instructor-led, live training, participants will take part in a series of discussions, exercises and case-study analysis to understand the fundamentals of Deep Learning. The most important Deep Learning tools and techniques will be evaluated and exercises will be carried out to prepare participants for carrying out their own evaluation and implementation of Deep Learning solutions within their organizations.

By the end of this training, participants will be able to:

• Understand the fundamentals of Deep Learning
• Learn Deep Learning techniques and their applications in the industry
• Examine issues in medicine which can be solved by Deep Learning technologies
• Explore Deep Learning case studies in medicine
• Formulate a strategy for adopting the latest technologies in Deep Learning for solving problems in medicine

Audience

• Managers
• Medical professionals in leadership roles

Format of the course

• Part lecture, part discussion, exercises and heavy hands-on practice

Note

• To request a customized training for this course, please contact us to arrange.

Course Outline

Introduction to Deep Learning

• Impact on the Medical Industry
• Successes and Failures in Deep Learning in Various Industries

Understanding Deep Learning

• Artificial Intelligence and Machine Learning
• Basic Concepts of Deep Learning
• Applications for Deep Learning
• The role of Big Data in Deep Learning 

Overview of Common Deep Learning Techniques

• Neural Networks
• Natural Language Processing
• Image Recognition
• Speech Recognition
• Sentiment Analysis

Applying Deep Learning Techniques to Issues in Medicine

• Exploring the Opportunities for Improvement in the Medical Field
• Examining the Applicability of Deep Learning Techniques to the Cited Issues

Exploring Deep Learning Case Studies for Medicine

• DeepVentricle Algorithm for Ventricular Segmentation in Cardiac MR by Arterys
• Skin Cancer Diagnosis Algorithm by Stanford
• Heart Failure Prediction Algorithm by Sutter Health and the Georgia Institute of Technology
• Radiology Scans Diagnoses Across All Modalities by Behold.AI
• Clinical Decision Support Technologies by Enlitic
• Personalized Medicine and Therapies by Deep Genomics
• Decoding Cancer with Freenome
• Detection of Diabetic Retinopathy by Google
• Chatbot for Prevention and Diagnosis of Disease by Babylon Health

Limitations of Deep Learning

Ethical Implications and Data Privacy Concerns in Deep Learning

Creating New Business Models Based on Deep Learning-Enabled Platforms and Ecosystems

Bringing it All Together

• Choosing Deep Learning Solutions that Fit Your Needs
• Strategies for Adoption of Deep Learning Technologies

Team Communication and Managerial Buy-In

• Conversations with Managers and Leaders
• Conversations with Engineers and Data Scientists

Summary and Conclusion

Duration

21 hours (usually 3 days including breaks)

Requirements

There are no specific requirements needed to attend this course.

Overview

Introduction:

Deep learning is becoming a principal component of future product design that wants to incorporate artificial intelligence at the heart of their models. Within the next 5 to 10 years, deep learning development tools, libraries, and languages will become standard components of every software development toolkit. So far Google, Sales Force, Facebook, Amazon have been successfully using deep learning AI to boost their business. Applications ranged from automatic machine translation, image analytics, video analytics, motion analytics, generating targeted advertisement and many more.

This coursework is aimed for those organizations who want to incorporate Deep Learning as very important part of their product or service strategy. Below is the outline of the deep learning course which we can customize for different levels of employees/stakeholders in an organization.

Target Audience:

( Depending on target audience, course materials will be customized)

Executives

A general overview of AI and how it fits into corporate strategy, with breakout sessions on strategic planning, technology roadmaps, and resource allocation to ensure maximum value.

Project Managers

How to plan out an AI project, including data gathering and evaluation, data cleanup and verification, development of a proof-of-concept model, integration into business processes, and delivery across the organization.

Developers

In-depth technical trainings, with focus on neural networks and deep learning, image and video analytics (CNNs), sound and text analytics (NLP), and bringing AI into existing applications.

Salespersons

A general overview of AI and how it can satisfy customer needs, value propositions for various products and services, and how to allay fears and promote the benefits of AI.

Course Outline

Day-1:

Basic Machine Learning

Module-1

Introduction:

• Exercise – Installing Python and NN Libraries
• Why machine learning?
• Brief history of machine learning
• The rise of deep learning
• Basic concepts in machine learning
• Visualizing a classification problem
• Decision boundaries and decision regions
• iPython notebooks

Module-2

• Exercise – Decision Regions
• The artificial neuron
• The neural network, forward propagation and network layers
• Activation functions
• Exercise – Activation Functions
• Backpropagation of error
• Underfitting and overfitting
• Interpolation and smoothing
• Extrapolation and data abstraction
• Generalization in machine learning

Module-3

• Exercise – Underfitting and Overfitting
• Training, testing, and validation sets
• Data bias and the negative example problem
• Bias/variance tradeoff
• Exercise – Datasets and Bias

Module-4

• Overview of NN parameters and hyperparameters
• Logistic regression problems
• Cost functions
• Example – Regression
• Classical machine learning vs. deep learning
• Conclusion

Day-2 : Convolutional Neural Networks (CNN)

Module-5

• Introduction to CNN
• What are CNNs?
• Computer vision
• CNNs in everyday life
• Images – pixels, quantization of color & space, RGB
• Convolution equations and physical meaning, continuous vs. discrete
• Exercise – 1D Convolution

Module-6

• Theoretical basis for filtering
• Signal as sum of sinusoids
• Frequency spectrum
• Bandpass filters
• Exercise – Frequency Filtering
• 2D convolutional filters
• Padding and stride length
• Filter as bandpass
• Filter as template matching
• Exercise – Edge Detection
• Gabor filters for localized frequency analysis
• Exercise – Gabor Filters as Layer 1 Maps

Module-7

• CNN architecture
• Convolutional layers
• Max pooling layers
• Downsampling layers
• Recursive data abstraction
• Example of recursive abstraction

Module-8

• Exercise – Basic CNN Usage
• ImageNet dataset and the VGG-16 model
• Visualization of feature maps
• Visualization of feature meanings
• Exercise – Feature Maps and Feature Meanings

Day-3 : Sequence Model

Module-9

• What are sequence models?
• Why sequence models?
• Language modeling use case
• Sequences in time vs. sequences in space

Module-10

• RNNs
• Recurrent architecture
• Backpropagation through time
• Vanishing gradients
• GRU
• LSTM
• Deep RNN
• Bidirectional RNN
• Exercise – Unidirectional vs. Bidirectional RNN
• Sampling sequences
• Sequence output prediction
• Exercise – Sequence Output Prediction
• RNNs on simple time varying signals
• Exercise – Basic Waveform Detection

Module-11

• Natural Language Processing (NLP)
• Word embeddings
• Word vectors: word2vec
• Word vectors: GloVe
• Knowledge transfer and word embeddings
• Sentiment analysis
• Exercise – Sentiment Analysis

Module-12

• Quantifying and removing bias
• Exercise – Removing Bias
• Audio data
• Beam search
• Attention model
• Speech recognition
• Trigger word Detection
• Exercise – Speech Recognition

Duration

28 hours (usually 4 days including breaks)

Requirements

• Experience with Python programming
• General familiarity with finance concepts
• Basic familiarity with statistics and mathematical concepts

Overview

Machine learning is a branch of Artificial Intelligence wherein computers have the ability to learn without being explicitly programmed. Deep learning is a subfield of machine learning which uses methods based on learning data representations and structures such as neural networks. Python is a high-level programming language famous for its clear syntax and code readability.

In this instructor-led, live training, participants will learn how to implement deep learning models for finance using Python as they step through the creation of a deep learning stock price prediction model.

By the end of this training, participants will be able to:

• Understand the fundamental concepts of deep learning
• Learn the applications and uses of deep learning in finance
• Use Python, Keras, and TensorFlow to create deep learning models for finance
• Build their own deep learning stock price prediction model using Python

Audience

• Developers
• Data scientists

Format of the course

• Part lecture, part discussion, exercises and heavy hands-on practice

Course Outline

Introduction

Understanding the Fundamentals of Artificial Intelligence and Machine Learning

Understanding Deep Learning

• Overview of the Basic Concepts of Deep Learning
• Differentiating Between Machine Learning and Deep Learning
• Overview of Applications for Deep Learning

Overview of Neural Networks

• What are Neural Networks
• Neural Networks vs Regression Models
• Understanding Mathematical Foundations and Learning Mechanisms
• Constructing an Artificial Neural Network
• Understanding Neural Nodes and Connections
• Working with Neurons, Layers, and Input and Output Data
• Understanding Single Layer Perceptrons
• Differences Between Supervised and Unsupervised Learning
• Learning Feedforward and Feedback Neural Networks
• Understanding Forward Propagation and Back Propagation
• Understanding Long Short-Term Memory (LSTM)
• Exploring Recurrent Neural Networks in Practice
• Exploring Convolutional Neural Networks in practice
• Improving the Way Neural Networks Learn

Overview of Deep Learning Techniques Used in Finance

• Neural Networks
• Natural Language Processing
• Image Recognition
• Speech Recognition
• Sentimental Analysis

Exploring Deep Learning Case Studies for Finance

• Pricing
• Portfolio Construction
• Risk Management
• High Frequency Trading
• Return Prediction

Understanding the Benefits of Deep Learning for Finance

Exploring the Different Deep Learning Libraries for Python

• TensorFlow
• Keras

Setting Up Python with the TensorFlow for Deep Learning

• Installing the TensorFlow Python API
• Testing the TensorFlow Installation
• Setting Up TensorFlow for Development
• Training Your First TensorFlow Neural Net Model

Setting Up Python with Keras for Deep Learning

Building Simple Deep Learning Models with Keras

• Creating a Keras Model
• Understanding Your Data
• Specifying Your Deep Learning Model
• Compiling Your Model
• Fitting Your Model
• Working with Your Classification Data
• Working with Classification Models
• Using Your Models

Working with TensorFlow for Deep Learning for Finance

• Preparing the Data
  • Downloading the Data
  • Preparing Training Data
  • Preparing Test Data
  • Scaling Inputs
  • Using Placeholders and Variables
• Specifying the Network Architecture
• Using the Cost Function
• Using the Optimizer
• Using Initializers
• Fitting the Neural Network
• Building the Graph
  • Inference
  • Loss
  • Training
• Training the Model
  • The Graph
  • The Session
  • Train Loop
• Evaluating the Model
  • Building the Eval Graph
  • Evaluating with Eval Output
• Training Models at Scale
• Visualizing and Evaluating Models with TensorBoard

Hands-on: Building a Deep Learning Model for Stock Price Prediction Using Python

Extending your Company’s Capabilities

• Developing Models in the Cloud
• Using GPUs to Accelerate Deep Learning
• Applying Deep Learning Neural Networks for Computer Vision, Voice Recognition, and Text Analysis

Summary and Conclusion

Duration

28 hours (usually 4 days including breaks)

Requirements

• Basic experience with R programming
• General familiarity with financial and banking concepts
• Basic familiarity with statistics and mathematical concepts

Overview

Machine learning is a branch of Artificial Intelligence wherein computers have the ability to learn without being explicitly programmed. Deep learning is a subfield of machine learning which uses methods based on learning data representations and structures such as neural networks. R is a popular programming language in the financial industry. It is used in financial applications ranging from core trading programs to risk management systems.

In this instructor-led, live training, participants will learn how to implement deep learning models for banking using R as they step through the creation of a deep learning credit risk model.

By the end of this training, participants will be able to:

• Understand the fundamental concepts of deep learning
• Learn the applications and uses of deep learning in banking
• Use R to create deep learning models for banking
• Build their own deep learning credit risk model using R

Audience

• Developers
• Data scientists

Format of the course

• Part lecture, part discussion, exercises and heavy hands-on practice

Course Outline

Introduction

Understanding the Fundamentals of Artificial Intelligence and Machine Learning

Understanding Deep Learning

• Overview of the Basic Concepts of Deep Learning
• Differentiating Between Machine Learning and Deep Learning
• Overview of Applications for Deep Learning

Overview of Neural Networks

• What are Neural Networks
• Neural Networks vs Regression Models
• Understanding Mathematical Foundations and Learning Mechanisms
• Constructing an Artificial Neural Network
• Understanding Neural Nodes and Connections
• Working with Neurons, Layers, and Input and Output Data
• Understanding Single Layer Perceptrons
• Differences Between Supervised and Unsupervised Learning
• Learning Feedforward and Feedback Neural Networks
• Understanding Forward Propagation and Back Propagation
• Understanding Long Short-Term Memory (LSTM)
• Exploring Recurrent Neural Networks in Practice
• Exploring Convolutional Neural Networks in practice
• Improving the Way Neural Networks Learn

Overview of Deep Learning Techniques Used in Banking

• Neural Networks
• Natural Language Processing
• Image Recognition
• Speech Recognition
• Sentimental Analysis

Exploring Deep Learning Case Studies for Banking

• Anti-Money Laundering Programs
• Know-Your-Customer (KYC) Checks
• Sanctions List Monitoring
• Billing Fraud Oversight
• Risk Management
• Fraud Detection
• Product and Customer Segmentation
• Performance Evaluation
• General Compliance Functions

Understanding the Benefits of Deep Learning for Banking

Exploring the Different Deep Learning Packages for R
    
Deep Learning in R with Keras and RStudio

• Overview of the Keras Package for R
• Installing the Keras Package for R
• Loading the Data
  • Using Built-in Datasets
  • Using Data from Files
  • Using Dummy Data
• Exploring the Data
• Preprocessing the Data
  • Cleaning the Data
  • Normalizing the Data
  • Splitting the Data into Training and Test Sets
• Implementing One Hot Encoding (OHE)
• Defining the Architecture of Your Model
• Compiling and Fitting Your Model to the Data
• Training Your Model
• Visualizing the Model Training History
• Using Your Model to Predict Labels of New Data
• Evaluating Your Model
• Fine-Tuning Your Model
• Saving and Exporting Your Model

Hands-on: Building a Deep Learning Credit Risk Model Using R

Extending your Company’s Capabilities

• Developing Models in the Cloud
• Using GPUs to Accelerate Deep Learning
• Applying Deep Learning Neural Networks for Computer Vision, Voice Recognition, and Text Analysis.

Summary and Conclusion

Duration

28 hours (usually 4 days including breaks)

Requirements

• Experience with Python programming
• General familiarity with financial and banking concepts
• Basic familiarity with statistics and mathematical concepts

Overview

Machine learning is a branch of Artificial Intelligence wherein computers have the ability to learn without being explicitly programmed. Deep learning is a subfield of machine learning which uses methods based on learning data representations and structures such as neural networks. Python is a high-level programming language famous for its clear syntax and code readability.

In this instructor-led, live training, participants will learn how to implement deep learning models for banking using Python as they step through the creation of a deep learning credit risk model.

By the end of this training, participants will be able to:

• Understand the fundamental concepts of deep learning
• Learn the applications and uses of deep learning in banking
• Use Python, Keras, and TensorFlow to create deep learning models for banking
• Build their own deep learning credit risk model using Python

Audience

• Developers
• Data scientists

Format of the course

• Part lecture, part discussion, exercises and heavy hands-on practice

Course Outline

Introduction

Understanding the Fundamentals of Artificial Intelligence and Machine Learning

Understanding Deep Learning

• Overview of the Basic Concepts of Deep Learning
• Differentiating Between Machine Learning and Deep Learning
• Overview of Applications for Deep Learning

Overview of Neural Networks

• What are Neural Networks
• Neural Networks vs Regression Models
• Understanding Mathematical Foundations and Learning Mechanisms
• Constructing an Artificial Neural Network
• Understanding Neural Nodes and Connections
• Working with Neurons, Layers, and Input and Output Data
• Understanding Single Layer Perceptrons
• Differences Between Supervised and Unsupervised Learning
• Learning Feedforward and Feedback Neural Networks
• Understanding Forward Propagation and Back Propagation
• Understanding Long Short-Term Memory (LSTM)
• Exploring Recurrent Neural Networks in Practice
• Exploring Convolutional Neural Networks in practice
• Improving the Way Neural Networks Learn

Overview of Deep Learning Techniques Used in Banking

• Neural Networks
• Natural Language Processing
• Image Recognition
• Speech Recognition
• Sentimental Analysis

Exploring Deep Learning Case Studies for Banking

• Anti-Money Laundering Programs
• Know-Your-Customer (KYC) Checks
• Sanctions List Monitoring
• Billing Fraud Oversight
• Risk Management
• Fraud Detection
• Product and Customer Segmentation
• Performance Evaluation
• General Compliance Functions

Understanding the Benefits of Deep Learning for Banking

Exploring the Different Deep Learning Libraries for Python

• TensorFlow
• Keras

Setting Up Python with the TensorFlow for Deep Learning

• Installing the TensorFlow Python API
• Testing the TensorFlow Installation
• Setting Up TensorFlow for Development
• Training Your First TensorFlow Neural Net Model

Setting Up Python with Keras for Deep Learning

Building Simple Deep Learning Models with Keras

• Creating a Keras Model
• Understanding Your Data
• Specifying Your Deep Learning Model
• Compiling Your Model
• Fitting Your Model
• Working with Your Classification Data
• Working with Classification Models
• Using Your Models

Working with TensorFlow for Deep Learning for Banking

• Preparing the Data
  • Downloading the Data
  • Preparing Training Data
  • Preparing Test Data
  • Scaling Inputs
  • Using Placeholders and Variables
• Specifying the Network Architecture
• Using the Cost Function
• Using the Optimizer
• Using Initializers
• Fitting the Neural Network
• Building the Graph
  • Inference
  • Loss
  • Training
• Training the Model
  • The Graph
  • The Session
  • Train Loop
• Evaluating the Model
  • Building the Eval Graph
  • Evaluating with Eval Output
• Training Models at Scale
• Visualizing and Evaluating Models with TensorBoard

Hands-on: Building a Deep Learning Credit Risk Model Using Python

Extending your Company’s Capabilities

• Developing Models in the Cloud
• Using GPUs to Accelerate Deep Learning
• Applying Deep Learning Neural Networks for Computer Vision, Voice Recognition, and Text Analysis

Summary and Conclusion