←BaldanAll skillsLet's talk

Skill 02 / 06

Neural networks that learn their own features from pixels, text and signals. Trained with TensorFlow, rebuilt from scratch, and small enough to run in your browser.

13

live demos

13

in the lab

6

step method

0

servers needed

How a neural network learns

Neurons, bends, and errors flowing backwards.

Before the projects: a tiny network trained live in your browser on real Jakarta air data, step by step.

00:0006:0012:0018:0023:00TYPICAL PM2.5 IN JAKARTA BY HOUR OF DAY (µg/m³)255075

How I do it

  1. 01

    Frame & collect

    Decide what goes in, what comes out and how it will be judged, then find data with a clear licence.

    Public datasetsLicence check
  2. 02

    Prepare tensors

    Scale, reshape and split, so the network sees clean numbers and the test set stays untouched.

    NumPyTrain / val / test
  3. 03

    Start simple

    A model with no hidden layer first: it sets the bar every deeper network has to clear.

    KerasBaselines
  4. 04

    Build the network

    Add the structure the data needs: convolutions for images, recurrence for sequences.

    Conv2DPoolingDropout
  5. 05

    Train for the real world

    Augment the training data and stop early, so the model survives inputs that don't look like the test set.

    AugmentationBackground swapsEarly stopping
  6. 06

    Shrink & ship

    Quantise the weights, re-test the small version, and run it where the user is.

    8-bit weightsTypeScript

Every project in the lab goes through these steps. Pick one and try it.

Go to the projects13

The toolkit

Networks are trained with Keras on TensorFlow, then every layer is re-implemented in TypeScript, so the demos need no TensorFlow.js and no server. The browser version is checked against Python on the full test set.

01 · Open data

Public image datasets with their licences, downloaded once and never committed.

hover or tap a logo ↑

02 · Train in Python

Networks built and trained with Keras on TensorFlow, compared against simpler baselines.

hover or tap a logo ↑

03 · Export

CNN weights stored as 8-bit integers with one scale per filter; LSTM weights as rounded floats.

hover or tap a logo ↑

04 · Run in your browser

Convolutions, pooling and dense layers written in TypeScript: no TensorFlow.js, no server.

hover or tap a logo ↑

The methodology

Split honestly

The test set is opened once, at the end.

Make it robust

Real inputs are messier than benchmarks.

  • Data augmentation

    Random rotation, shift, zoom, flips and brightness while training

  • Stress tests

    The same test set shifted, rotated, shrunk, darkened or on new backgrounds

  • Background swaps

    Breaking the 'white = background' shortcut with random textures

  • Identity before counting

    Boxes are tracked frame to frame and each track is counted once, so one car isn't counted thirty times

  • Smoothed and debounced

    One Euro filtering for pointers; two thresholds for the pinch; a minimum and maximum blink length; notes and chords that only change once the hand clearly moves

  • Hand rules tested on real hands

    Finger counting, fists and thumb taps checked on real hand landmarks before shipping

  • Calibrated to each face

    Measured against the visitor's own relaxed face, open eyes or neutral head pose, so natural differences don't count

  • Same framing as training

    Visitors' strokes are cropped, scaled and centred exactly like the dataset's bitmaps

  • Landmarks, not pixels

    21 hand points carry the shape and nothing about the background

Shrink honestly

A smaller model is a different model: test it again.

Look at the mistakes

Accuracy hides which errors happen and why.

The lab

Next skill

Data Analytics & BI

Questions answered with SQL, charts and dashboards.

Open