Expert level Data and Machine Learning

Deep Learning and Production ML Systems

Train neural networks, work with text, then take a model into production: serve it, test it, monitor it for drift, schedule data pipelines, design experiments properly and review risks, finishing with an end-to-end ML system reviewed by the NIBVEDA team.

  • 42hours of work
  • 19parts
  • Reviewedcapstone
  • Lifetimeaccess
  • PyTorch
  • NLP
  • Model serving
  • MLOps
  • Drift monitoring
  • Data pipelines
  • Experiment design
  • Responsible ML

At a glance

Who it is for

Practitioners who build validated models with scikit-learn and want to learn deep learning and how to run machine-learning systems reliably.

Before you start

Solid Python, pandas and scikit-learn, comfort with Git and the command line, and basic Docker. A computer able to train small neural networks (a CPU is enough; free notebook GPUs help). The Intermediate programme or equivalent experience is recommended.

How you finish

Pass the quizzes and labs, then submit a capstone project. The NIBVEDA team reviews it and either accepts it or sends it back with comments you can act on.

What you will be able to do

  1. 01Build and train neural networks in PyTorch and recognise overfitting and unstable training
  2. 02Classify text with classic methods and with pretrained embeddings
  3. 03Serve a model through a tested, versioned API in a container
  4. 04Detect data drift and degrade gracefully, with monitoring and retraining rules
  5. 05Build idempotent, scheduled data pipelines
  6. 06Design and analyse experiments and judge when a model's effect is real
  7. 07Write a risk and privacy review for an ML system

Curriculum 42 hours in 19 parts

Select a kind to highlight its parts.

Stage 1A classifier on text or images, end to end7 parts · 11 h
  1. 1
    Neural network fundamentalsLesson · Short, focused reading with questions to check yourself.
    1 hFree
  2. 2
    Training deep models wellLesson · Short, focused reading with questions to check yourself.
    1 h
  3. 3
    Train a neural network with PyTorchWorkshop · Follow along and build, with the steps and the traps written out.
    2 h
  4. 4
    Working with text: from counts to embeddingsLesson · Short, focused reading with questions to check yourself.
    1 h
  5. 5
    Classify text with a baseline and a neural modelWorkshop · Follow along and build, with the steps and the traps written out.
    2 h
  6. 6
    Check yourself: deep learning and textQuiz · Twelve questions, marked at once, with the reason behind each answer.
    1 h
  7. 7
    A classifier on text or images, end to endLab · Hands-on work. Many labs are checked automatically against what must exist.
    3 h
Stage 2Package, test and containerise a model service6 parts · 10 h
  1. 8
    ML systems: from a notebook to a serviceLesson · Short, focused reading with questions to check yourself.
    1 h
  2. 9
    Serve a model through a tested, versioned APIWorkshop · Follow along and build, with the steps and the traps written out.
    2 h
  3. 10
    Monitoring models and detecting driftLesson · Short, focused reading with questions to check yourself.
    1 h
  4. 11
    Detect drift and decide when to retrainWorkshop · Follow along and build, with the steps and the traps written out.
    2 h
  5. 12
    Check yourself: production machine learningQuiz · Twelve questions, marked at once, with the reason behind each answer.
    1 h
  6. 13
    Package, test and containerise a model serviceLab · Hands-on work. Many labs are checked automatically against what must exist.
    3 h
Stage 3A tested retraining pipeline4 parts · 8 h
  1. 14
    Reliable, idempotent data pipelinesWorkshop · Follow along and build, with the steps and the traps written out.
    2 h
  2. 15
    A/B tests and causal pitfallsWorkshop · Follow along and build, with the steps and the traps written out.
    2 h
  3. 16
    Check yourself: pipelines and experimentsQuiz · Twelve questions, marked at once, with the reason behind each answer.
    1 h
  4. 17
    A tested retraining pipelineLab · Hands-on work. Many labs are checked automatically against what must exist.
    3 h
Stage 4Model card, privacy and risk review1 part · 3 h
  1. 18
    Model card, privacy and risk reviewLab · Hands-on work. Many labs are checked automatically against what must exist.
    3 h
FinishCapstone project1 part · 10 h
  1. 19
    An end-to-end ML systemCapstone · A full project for your portfolio.
    10 h
Free lessonNeural network fundamentals
What you take away

An internship certificate with your skills on it.

Made for you automatically when you finish the last part, it names the internship programme, the level and the 42 hours, lists what you showed, and carries a number and a QR code. Anyone can check it on the NIBVEDA verification page, and it shows as withdrawn there if it is ever revoked.

  • Proof you completed all 42 hours of this internship programme
  • An Internship badge for your profile, CV or portfolio
  • Not a job, a stipend or an academic degree, and it says so

See how verification works

More in Data and Machine Learning

Keep building.

3 programmes in this track, from beginner to expert. Buy the learning path and save 15%.

IntermediateIntermediate40 h Build and Validate Real Predictive Models

Go beyond your first model. Engineer features, validate without fooling yourself, handle imbalanced data and time series, explain what a model learned, and track experiments reproducibly, finishing with a predictive-model report reviewed by the NIBVEDA team.

  • Feature engineering
  • Cross-validation
  • Gradient boosting
Rs. 649 + GST
BeginnerBeginner40 h From a Spreadsheet to Your First Model

Learn Python for data, clean and explore a real dataset, and train and honestly evaluate your first machine-learning model, finishing with a short report of your own.

  • Python
  • pandas
  • Data cleaning
Rs. 349 + GST

See all 3 programmes in Data and Machine Learning Take the placement test

Before you enrol

Quick answers.

The policies have the full detail.

Refund policy Terms of use

Is this a real internship?

It is a virtual internship programme: a structured, self-paced course built around a real project, with checked assessments and a certificate. It is not employment, it does not carry a stipend and it is not an academic or AICTE-approved qualification. What it gives you is verified, project-based evidence of skills.

How does self-paced work?

You start when you like and move at your own speed. Each part unlocks when you finish the one before it. There are no live classes and no deadlines. Your access is shown on each programme page.

How is my work checked?

Quizzes are marked as soon as you submit them. Labs use a tick-list of tasks. Intermediate and Expert programmes finish with a capstone that the NIBVEDA team reviews and either accepts or sends back with comments.

Can I get a refund?

Please read the refund policy before you buy. It explains when a refund is possible.

Ready to start?

Rs. 1,178.82 including GST. Lifetime access. Read the first lesson free before you decide.

Compare programmes