Deep Learning Specialization · Sequence Models

Neural Machine Translation with Attention

A date-normalization model that uses a seq2seq architecture with attention to translate human-readable dates into YYYY-MM-DD format.

Seq2SeqAttention mechanismBi-LSTM encoderDecoder LSTMAlignment visualization

GitHub

What this project is about

The translation task normalizes human-written dates into machine-readable format. Attention lets the decoder focus on relevant input positions while producing each output character.

Implementation focus

The learning was alignment: the model does not need to compress everything into one vector; it can dynamically look back at the source sequence.

Key results and artifacts

Dataset: 10,000 examples
Input length: 30; output length: 10
Examples translated dates like “5 April 09” → 2009-04-05

What I learned

The most important idea was alignment: the decoder can learn where to look in the input while producing each output character.

Milestone deep dive

What this project proves in my learning path.

A date-normalization model that uses a seq2seq architecture with attention to translate human-readable dates into YYYY-MM-DD format. The milestone is included because it shows a complete learning unit: a problem, a data representation, an implementation path, measurable outputs, and a lesson that later connects to larger AI systems.

Input layertokens, masks, and embeddings

Model layerattention-based sequence architecture

Evaluation layertests, metrics, plots, or qualitative output

Artifact layercontext-aware sequence representations or generated tokens

Problem framing

What I was trying to solve

This page is not just a lab description. It explains how I transformed the assignment idea into an engineering story: what the model receives, what it optimizes, what output it should produce, and how the result can be inspected.

Implementation

What I coded or assembled

The implementation focus was the mechanism behind the result: functions, model blocks, training logic, preprocessing, evaluation, and the small technical details that make the notebook work rather than only look correct.

Concepts

Core concepts

Seq2SeqAttention mechanismBi-LSTM encoderDecoder LSTMAlignment visualization

These tags show the technical ideas this milestone added to my toolkit.

Learning result

What changed after it

The most important idea was alignment: the decoder can learn where to look in the input while producing each output character.

Important outputs and evidence

Dataset: 10,000 examples
Input length: 30; output length: 10
Examples translated dates like “5 April 09” → 2009-04-05

How I would explain it in an interview

I would describe this milestone by starting from the data representation, then explain the model or algorithm, then show what was measured. The important part is not only the final number; it is the ability to reason about why the method works, what assumptions it makes, and what limitations should be improved next.