ai_book

ai_book copied to clipboard

Understanding Black-box Predictions via Influence Functions

2

### Abstract - Use influence function to trace a model's prediction back to its training data. - Approximation of influence function that requires gradients and Hessian vectors provides valuable information...

YeonwooSung

1. Euclidean distance Euclidean distance (often called L2 norm) is the most intuitive of the metrics.  However, the Euclidean distance only considers the size not orientation (direction of the...

YeonwooSung

Using Fast Weights to Attend to the Recent Past

2

The authors [1] propose "fast weights", a type of attention mechanism to the recent past that performs multiple steps of computation between each hidden state computation step in an RNN....

YeonwooSung

CRF (Conditional Random Fields)

1

[Ratsgo's blog](https://ratsgo.github.io/machine%20learning/2017/11/10/CRF/)

YeonwooSung

Few-Shot Learning with Class Imbalance

1

E. Triantafillou et. al. [1] had experiments for few-shot learning with class imbalance to see if the class imbalance actually impacts to the performance of the few-shot learning methods. **Results**...

YeonwooSung

Radioactive data: tracing through training

1

### Abstract - Neural classifiers can improve their performance by training on more data - But given a trained classifier, it's difficult to tell what data it was trained on...

YeonwooSung

Modeling Recurrence for Transformer

1

### Abstract - propose additional "Attentive Recurrent Network(ARN)" to Transformer encoder to leverage the strengths of both attention and recurrent networks - WMT14 EnDe and WMT17 ZhEn demonstrates the effectiveness...

YeonwooSung

### Abstract - Augmenting RNN with Attention is a new trend. - A human with a piece of paper is, in some sense, much smarter than a human without. -...

YeonwooSung

### Abstract - **Yes** for the case of soft attention: somewhat mixed result across tasks. - Active memory operates on all of the memory in parallel in a uniform way,...

YeonwooSung

Bumps the pip group with 1 update in the /Experiments/CV/ocr_with_bert directory: [requests](https://github.com/psf/requests). Bumps the pip group with 1 update in the /LLMs/RAG/llama-index-milvus-example directory: [requests](https://github.com/psf/requests). Bumps the pip group with 1...

dependabot[bot]