Deep Learning with TensorFlow 2 (TF2) and Keras
Gain hands‑on skills to build, train, and evaluate neural‑network models for regression, classification, computer‑vision, text‑analytics, and time‑series tasks using TensorFlow 2 and Keras.
Get Course Info
Audience: Developers / Data Analysts / Data Scientists
Duration: 3 days
Format: Lectures and hands‑on labs (50% lecture, 50% lab)
Overview
The abundance of data and affordable cloud scale has led to an explosion of interest in Deep Learning. Google has open‑sourced a library called TensorFlow which has become the de‑facto standard, allowing state‑of‑the‑art machine learning done at scale, complete with GPU‑based acceleration. This course introduces Deep Learning concepts and the TensorFlow 2 / Keras libraries to students.
Objective
Gain hands‑on skills to build, train, and evaluate neural‑network models for regression, classification, computer‑vision, text‑analytics, and time‑series tasks using TensorFlow 2 and Keras.
What You Will Learn
- Deep Learning concepts
- TensorFlow 2 and Keras APIs
- Creating neural networks with TensorFlow 2 / Keras
- Using TensorBoard for visualising training
- Building models for Regression, Classification, Computer Vision, Text Analytics, and Time Series
- Transfer‑learning techniques and benchmarking on CPU vs. GPU
Course Details
Audience: Developers / Data Analysts / Data Scientists
Duration: 3 days
Format: Lectures and hands‑on labs (50% lecture, 50% lab)
Basic knowledge of Python language and Jupyter notebooks is assumed (Python resources provided).
Setup: Cloud‑based lab environment (zero‑install) • Modern laptop with unrestricted Internet • Chrome browser
Detailed Outline
- Understanding DL use��cases
- AI / ML / DL taxonomy, data & AI vocabulary
- Hardware & software ecosystem
- Supervised / Unsupervised / Reinforcement learning
- TensorFlow overview & execution graph
- GPU / TPU acceleration
- TensorFlow API landscape
- Lab: Setting up and running TensorFlow
- Keras concepts: models & layers
- Using Keras Sequential and Functional APIs
- Lab exercises
- Perceptrons & activation functions (Sigmoid, Tanh, ReLU, Softmax)
- Back‑propagation & optimisers (GD, Adam, RMSProp)
- Loss functions for regression & classification
- Vanishing / exploding gradients
- Lab: TensorFlow playground
- FFNN architecture: input, hidden, output layers
- Sizing deep networks
- Lab: FFNNs
- CNN architecture & concepts
- Lab: Image recognition using CNNs
- RNN architecture, LSTM networks
- Lab: RNNs for text & sequence prediction
- Transfer‑learning concepts
- Customising pre‑trained models
- Lab: transfer‑learning & performance benchmarking
- Team project solving a real‑world use‑case
Ready to Get Started?
Contact us to learn more about this course and schedule your training.