Interactive Mentor-Led Cohorts

(02) 8902 0900contact@aumtrend.comWhatsApp / Viber
AUM Training
HomeCourses
Who We Serve
About UsContact
LMS Portal
DEEP LEARNING
20 Hours (10 Days × 2 Hours)
View Full Curriculum

Deep Learning with TensorFlow & Keras

By the end of this course, participants will be able to design, train, evaluate, and fine-tune Deep Learning models using TensorFlow and Keras for Computer Vision, Natural Language Processing, and Transfer Learning production workflows.

Live Interactive Syllabus
20 Hours (10 Days × 2 Hours)
•
Instructor-Led Online
•
10 Hands-on Coding Labs
What you'll master in Level 2
Target Competency Outcome

By the end of this course, participants will be able to design, train, evaluate, and fine-tune Deep Learning models using TensorFlow and Keras for Computer Vision, Natural Language Processing, and Transfer Learning production workflows.

Training Objectives & Core Deliverables

Understand artificial neural network architectures, activation functions, and backpropagation.

Build, compile, train, and evaluate deep neural networks using TensorFlow and Keras APIs.

Design and train Convolutional Neural Networks (CNN) for image classification on datasets like Fashion MNIST.

Implement text preprocessing, tokenization, word embeddings, and sequence models (RNN/LSTM) for sentiment analysis.

Leverage Transfer Learning with pretrained vision backbones like MobileNet and ResNet.

Export and serialize trained deep learning models for production inference.

Day-by-Day Training Schedule & Live Labs
10 Live Sessions • 100% Hands-on
Day 1
Module 1 – Deep Learning Fundamentals
Live Session
Topics Explored:
Evolution from Machine Learning to Deep Learning
Biological neuron vs Artificial neuron
Perceptron and Multilayer Perceptron (MLP)
Neural Network architecture
Activation functions: Sigmoid, ReLU, Tanh, Softmax
Hands-on Lab Exercise

Explore perceptron logic and neural network forward pass calculations.

Day 2
Module 1 – Deep Learning Fundamentals
Live Session
Topics Explored:
Forward propagation and Backpropagation
Gradient Descent, Loss functions, and optimizers
Hands-on Lab Exercise

Lab Practical: Build a basic ANN for a classification problem.

Day 3
Module 2 – Tensor Flow & Keras for Deep Learning
Live Session
Topics Explored:
Tensors and operations in TensorFlow
TensorFlow ecosystem overview
Keras Sequential and Functional APIs
Building neural networks layer by layer
Hands-on Lab Exercise

Create and manipulate multi-dimensional tensors and construct sequential neural layers.

Day 4
Module 2 – Tensor Flow & Keras for Deep Learning
Live Session
Topics Explored:
Training, validation, and loss tracking
Early stopping and model checkpoint callbacks
Saving and loading models for inference
Hands-on Lab Exercise

Lab Practical: Customer churn prediction using TensorFlow/Keras.

Day 5
Module 3 – Computer Vision with CNN
Live Session
Topics Explored:
Image representation in digital tensors
Convolution layer, filters, and feature maps
Pooling layers (Max, Average)
Flatten and Dense classification layers
Hands-on Lab Exercise

Inspect convolutional feature maps and filter transformations on image tensors.

Day 6
Module 3 – Computer Vision with CNN
Live Session
Topics Explored:
CNN architecture design & tuning
Loading image datasets & normalization
Data augmentation (conceptual)
Hands-on Lab Exercise

Lab Practical: Fashion MNIST image classification.

Day 7
Module 4 – NLP with Deep Learning
Live Session
Topics Explored:
NLP Foundations & text cleaning pipelines
Stop words, Stemming, and Lemmatization overview
Tokenization and vocabulary indexing
Word embeddings (Dense vector representations)
Hands-on Lab Exercise

Build text tokenization, vocabulary indexing, and dense word embedding vectors.

Day 8
Module 4 – NLP with Deep Learning
Live Session
Topics Explored:
Sequence Models: RNN and LSTM architecture
Text classification workflow
Hands-on Lab Exercise

Lab Practical: Sentiment analysis using TensorFlow/Keras.

Day 9
Module 5 – Transfer Learning & Capstone Project
Live Session
Topics Explored:
Why pretrained models are standard practice
MobileNet, ResNet, and EfficientNet architectures
Fine-tuning pretrained models with frozen backbones
Model evaluation, confusion matrix, and inference
Hands-on Lab Exercise

Load and fine-tune a pretrained MobileNet/ResNet model on a custom image dataset.

Day 10
Module 5 – Transfer Learning & Capstone Project
Live Session
Topics Explored:
Exporting trained models for production
Production inference optimization and serialization
Hands-on Lab Exercise

Lab Practical: End-to-end image classification project using transfer learning.

Track Portfolio Capstone Project

End-to-End Deep Learning Transfer Learning Project: A production-ready computer vision application utilizing pretrained MobileNet/ResNet architectures, custom classification heads, early stopping callbacks, and exported inference models with evaluation matrices.

Detailed Module-wise Curriculum
5 Modules

Evolution from Machine Learning to Deep Learning

Biological neuron vs Artificial neuron

Perceptron and Multilayer Perceptron (MLP)

Neural Network architecture

Activation functions: Sigmoid, ReLU, Tanh, Softmax

Forward propagation and Backpropagation

Gradient Descent, Loss functions, and optimizers

Lab Practical: Build a basic ANN for a classification problem.

Tensors and operations in TensorFlow

TensorFlow ecosystem overview

Keras Sequential and Functional APIs

Building neural networks layer by layer

Training, validation, and loss tracking

Early stopping and model checkpoint callbacks

Saving and loading models for inference

Lab Practical: Customer churn prediction using TensorFlow/Keras.

Image representation in digital tensors

Convolution layer, filters, and feature maps

Pooling layers (Max, Average)

Flatten and Dense classification layers

CNN architecture design & tuning

Loading image datasets & normalization

Data augmentation (conceptual)

Lab Practical: Fashion MNIST image classification.

NLP Foundations & text cleaning pipelines

Stop words, Stemming, and Lemmatization overview

Tokenization and vocabulary indexing

Word embeddings (Dense vector representations)

Sequence Models: RNN and LSTM architecture

Text classification workflow

Lab Practical: Sentiment analysis using TensorFlow/Keras.

Why pretrained models are standard practice

MobileNet, ResNet, and EfficientNet architectures

Fine-tuning pretrained models with frozen backbones

Model evaluation, confusion matrix, and inference

Exporting trained models for production

Lab Practical: End-to-end image classification project using transfer learning.
DEEP LEARNING COMPETENCY BADGE
Certificate of Technical Competency — Deep Learning with TensorFlow & Keras

Complete all live hands-on labs to earn this verifiable competency badge. This credential unlocks progression to Generative AI, Large Language Models & Prompt Engineering.

LIVE ONLINE COHORT
Admissions Open
Enroll in Deep Learning with TensorFlow & Keras
Reserve your seat for upcoming live batches, syllabus consultation & fee structure.
Selected Course Program *
100% Privacy. Official Admissions Desk.

Frequently Asked Questions

Frequently Asked Questions: Generative AI Training Plan

Find clear answers to common questions about our live interactive classes, cohort schedules, project mentoring, and career assistance.

This program is designed for engineers, developers, and tech professionals looking to master applied Machine Learning, Deep Learning, Generative AI, autonomous Agentic AI systems, and practical workplace prompt engineering.

You can choose to enroll in the complete 5-track master program (recommended for end-to-end expertise) or consult our academic team to join specific tracks matching your current skills.

Track 1: Scikit-learn, MLOps, ML Pipelines. Track 2: TensorFlow, Keras, CNN, NLP. Track 3: LangChain, Chroma/FAISS, RAG, Fine-Tuning. Track 4: LangGraph, MCP, ReAct, Multi-Agent Systems. Track 5: Prompt Engineering, Reusable Template Libraries & Risk Management.

Yes, all classes are live, interactive online sessions with senior practitioners. Session recordings, code notebooks, datasets, and reading references are shared after each class.

Still have questions? We're here to help!

Speak directly with our technical advisors to discuss cohorts, curriculum, and career assistance.

FREE 1-ON-1 ACADEMIC GUIDANCE

Ready to Start Your Tech Journey?

Connect with our academic training counsellors. We analyze your background, career goals, and recommend the best live online track for your success.

Call Helpline: (02) 8902 0900WhatsApp or Viber Support