.learn() - page 5

Trimming constructor arguments with dependency injection: MVVM and the .NET Host

How DI simplifies object creation, and how the .NET Generic Host keeps the ever-growing constructors of MVVM view models short.

csharp  dependency-injection  mvvm  design-pattern

software-engineering

2025-01-20   ·   3 min read

CS6515: Graduate Algorithms · Part 1

Dynamic Programming

How overlapping subproblems and optimal substructure turn recursive definitions into efficient algorithms.

cs6515  dynamic-programming

algorithms

2024-07-26   ·   1 min read

From Seq2Seq to Transformer: from accumulated context to direct reference · Part 4

Self-attention and the Transformer - cutting the sequential chain and referencing directly

Where an RNN passed context along by accumulating it through previous states, the Transformer looks up the tokens it needs directly. How self-attention removes the sequential structure, and how it connects back to attention Seq2Seq.

transformer  self-attention  multi-head-attention  positional-encoding  masked-attention

deep-learning

2023-07-14   ·   4 min read

From Seq2Seq to Transformer: from accumulated context to direct reference · Part 3

The decoder's remaining problem - output context still accumulates

Attention solved the encoder-side information bottleneck. But the decoder itself is still a sequential structure that depends on its previous state. Here is why that becomes the final motivation for the Transformer.

attention  seq2seq  bahdanau-attention  query-key-value  nlp

deep-learning

2023-06-28   ·   3 min read

From Seq2Seq to Transformer: from accumulated context to direct reference · Part 2

Attention Seq2Seq - don't just look at the last state, look directly

How do you fix the vanilla Seq2Seq bottleneck? By letting the decoder reference every encoder hidden state directly, "as needed".

attention  seq2seq  bahdanau-attention  query-key-value  nlp

deep-learning

2023-06-02   ·   4 min read