AI for Text Images and Forecasting

Build and evaluate neural‑network models for structured data, images, text, and temporal signals using TensorFlow & Keras in cloud labs.

Get Course Info

Audience: Developers / Data Analysts / Data Scientists

Duration: 3 days

Format: Lectures and hands‑on labs (50% lecture, 50% lab)

Overview

This course introduces Deep Learning concepts and TensorFlow/Keras libraries to solve industry use‑cases across regression, classification, computer vision, text analytics, and time‑series forecasting.

Objective

Build and evaluate neural‑network models for structured data, images, text, and temporal signals using TensorFlow & Keras in cloud labs.

What You Will Learn

Deep Learning foundations
TensorFlow & Keras tool‑chain
Neural‑network design for multiple data modalities
TensorBoard for training introspection
Industry case‑studies: finance, healthcare, customer service, NLP, computer vision
Hands‑on labs for each modality

Course Details

Audience: Developers / Data Analysts / Data Scientists

Duration: 3 days

Format: Lectures and hands‑on labs (50% lecture, 50% lab)

Prerequisites:

Basic Python & Jupyter familiarity (resources provided for newcomers).

Setup: Cloud‑based lab • Modern laptop • Chrome browser

Detailed Outline

DL use‑cases & AI taxonomy
Data & AI vocabulary
Hardware & software ecosystem

TensorFlow execution graph, GPU/TPU
Keras model/layer APIs
Lab setup

Perceptrons, activation functions, back‑prop, optimisers, loss functions
Lab: TensorFlow playground

FFNN architecture & sizing
CNN intro, architecture, lab on image recognition

RNN architecture & LSTM
Labs on text analytics: spam detection, sentiment analysis, review classification

Building RNN/LSTM models for temporal data
Case‑study: stock price prediction

Transfer‑learning workflows
Benchmarking CPU vs. GPU

Team project on real‑world dataset