2-Day Deep Learning with TensorFlow (LIVE Stream)
The Complete Guide to Understanding TensorFlow for Machine & Deep Learning for Artificial Intelligence
Tensorflow is the Most Popular Open Source Deep Learning Framework (Google)
Much of the world’s data is unstructured. Think images, sound, and textual data. Learn how to apply Deep Learning with TensorFlow to this type of data to solve real-world problems.
Tensorflow is the most popular and powerful open source machine learning/deep learning framework developed by Google for everyone. It is one of the best libraries to implement deep learning. TensorFlow is a software library for numerical computation of mathematical expressional, using data flow graphs. Nodes in the graph represent mathematical operations, while the edges represent the multidimensional data arrays (tensors) that flow between them.
Tensorflow has many powerful Machine Learning API such as Neural Network, Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Word Embedding, Seq2Seq, Generative Adversarial Networks (GAN), Reinforcement Learning, and Meta Learning.
Learn & Add this In-Demand Skills to Your Skills Set
Gain the core knowledge to Tensorflow for Deep Learning and Machine Learning. Let our Data Scientist share with you the core foundation of TensorFlow and work our way through the necessary concepts and APIs so as to be able to write distributed machine learning models. Given a TensorFlow model, we explain how to scale out the training of that model and offer high-performance predictions using Cloud Machine Learning Engine. Upon wrapping up this course, you’ll have the knowledge you need to continue your coding journey in whichever language piques your interest.
In this hands-on 2 Day TensorFlow course, you will learn the basic concepts of TensorFlow, the main functions, operations and the execution pipeline. Starting with a simple “Hello Word” example, throughout the course you will be able to see how TensorFlow can be used in curve fitting, regression, classification and minimization of error functions.
- Understanding of the subtle differences between machine and deep learning
- Explain foundational TensorFlow concepts such as the main functions, operations and the execution pipelines.
- Describe how TensorFlow can be used in curve fitting, regression, classification and minimization of error functions.
- Understand different types of Deep Architectures, such as Convolutional Networks, Recurrent Networks and Autoencoders.
- Understand how Neural Networks Work for Classification and Regression Tasks
- Learn Basic Tensorflow 2 operations
- How to use TensorFlow for Time Series Analysis with Recurrent Neural Networks
- Use TensorFlow for solving Unsupervised Learning Problems with AutoEncoders
- Create Generative Adversarial Networks with TensorFlow
- Understand how to build neural network models using tensorflow and keras on particular use cases
- Recurrent Neural Network for Sequential Data
Who Should Attend?
- Individuals with a basic understanding of Python Programming and are seeking more advanced coding skills.
- Machine Learning Engineers, and Developers, Data Analyst, Programmers, IT Engineers & Data Scientist.
Note: Participant is required to bring their own laptop with access to internet (WiFi network will be provided)
Mr Solomon Soh, ACTA certified has trained and coached over 100 professionals in the area of data science, python programming and coding. Solomon is a Certified AI Engineer Associate by AI Singapore and holds certifications in Alibaba Cloud Architect and Alteryx respectively. Solomon interests include Reinforcement Learning, Natural Language Processing and Time-Series analysis.
Topic 1 Overview of Machine Learning & Tensorflow
• Machine Learning vs Deep Learning
• Introduction to Tensorflow
• Install Tensorflow 2.x
Topic 2 Basic Operations with Tensorflow
• Basic Tensor Data Types
• Constant, Variable & Gradient
• Matrix Operations
Topic 3 Important Datasets and pre-processing steps
• Tabular datasets (Pima Diabetic Dataset)
• MNIST Hand written digit Dataset
• MNIST Fashion Datasets
• CIFAR-10 Image Dataset
Topic 4 Fully connected Neural Network (FcNN)
• Introduction to Neural Network (NN)
• Activation Functions (Sigmoid, ReLU, etc.)
• Loss Function and Optimizer
• Learning rate and gradient calculation
• Build Regression Model with FcNN
• Load and Save Model
• Build Classification Model with FcNN
• Softmax activation function for classification
• Exercise: Classification model building with Image data
• Ladder wise and End-to-End Training
• Fine Tune the model
Topic 5 Fully Connected Auto Encoder
• What is Auto-encoder?
• Importance of Auto-encoder
• De-noising Auto-encoder
• Build Auto-Encoder model with MNIST dataset
Topic 6 Convolutional Neural Network (CNN)
• Introduction to Convolutional Neural Network (CNN)
• FcNN vs CNN
• Convolution, Stride, Padding, and Activation
• Pooling (Max-pooling and Average pooling)
• Build CNN-based Image classification models.
• Exercise (Model building for dog-cat dataset)
• Model Fine-tuning
• Data Augmentation & Dropout
Topic 7 Transfer Learning
• Pre-trained Deep-CNN models
• Vgg16, Resnet34, InceptionV3, DenseNet, etc.
• Fine tuning of pre-trained models
Topic 8 Recurrent Neural Network (RNN)
• Sequential Data (Language, music, DNA, speech, etc.)
• What is Recurrent Neural Network (RNN)?
• Types of RNN Architectures
• Handling long term dependencies with LSTM cells
• Word Embedding
• Build a RNN Model for Text Classification