Benjamin Paine's picture

Benjamin Paine PRO

benjamin-paine

AI & ML interests

A software engineer with an AI habit

Recent Activity

updated a model about 9 hours ago
benjamin-paine/demo-outputs
reacted to Kseniase's post with 🔥 about 14 hours ago
15 types of attention mechanisms Attention mechanisms allow models to dynamically focus on specific parts of their input when performing tasks. In our recent article, we discussed Multi-Head Latent Attention (MLA) in detail and now it's time to summarize other existing types of attention. Here is a list of 15 types of attention mechanisms used in AI models: 1. Soft attention (Deterministic attention) -> https://huggingface.co/papers/1409.0473 Assigns a continuous weight distribution over all parts of the input. It produces a weighted sum of the input using attention weights that sum to 1. 2. Hard attention (Stochastic attention) -> https://huggingface.co/papers/1508.04025 Makes a discrete selection of some part of the input to focus on at each step, rather than attending to everything. 3. Self-attention -> https://huggingface.co/papers/1706.03762 Each element in the sequence "looks" at other elements and "decides" how much to borrow from each of them for its new representation. 4. Cross-Attention (Encoder-Decoder attention) -> https://huggingface.co/papers/2104.08771 The queries come from one sequence and the keys/values come from another sequence. It allows a model to combine information from two different sources. 5. Multi-Head Attention (MHA) -> https://huggingface.co/papers/1706.03762 Multiple attention “heads” are run in parallel.​ The model computes several attention distributions (heads), each with its own set of learned projections of queries, keys, and values. 6. Multi-Head Latent Attention (MLA) -> https://huggingface.co/papers/2405.04434 Extends MHA by incorporating a latent space where attention heads can dynamically learn different latent factors or representations. 7. Memory-Based attention -> https://huggingface.co/papers/1503.08895 Involves an external memory and uses attention to read from and write to this memory. See other types in the comments 👇
liked a model 1 day ago
benjamin-paine/steamboat-willie-1.3b
View all activity

Organizations

Taproot AI's profile picture

benjamin-paine's activity

reacted to Kseniase's post with 🔥 about 14 hours ago
view post
Post
1634
15 types of attention mechanisms

Attention mechanisms allow models to dynamically focus on specific parts of their input when performing tasks. In our recent article, we discussed Multi-Head Latent Attention (MLA) in detail and now it's time to summarize other existing types of attention.

Here is a list of 15 types of attention mechanisms used in AI models:

1. Soft attention (Deterministic attention) -> Neural Machine Translation by Jointly Learning to Align and Translate (1409.0473)
Assigns a continuous weight distribution over all parts of the input. It produces a weighted sum of the input using attention weights that sum to 1.

2. Hard attention (Stochastic attention) -> Effective Approaches to Attention-based Neural Machine Translation (1508.04025)
Makes a discrete selection of some part of the input to focus on at each step, rather than attending to everything.

3. Self-attention -> Attention Is All You Need (1706.03762)
Each element in the sequence "looks" at other elements and "decides" how much to borrow from each of them for its new representation.

4. Cross-Attention (Encoder-Decoder attention) -> Cross-Attention is All You Need: Adapting Pretrained Transformers for Machine Translation (2104.08771)
The queries come from one sequence and the keys/values come from another sequence. It allows a model to combine information from two different sources.

5. Multi-Head Attention (MHA) -> Attention Is All You Need (1706.03762)
Multiple attention “heads” are run in parallel.​ The model computes several attention distributions (heads), each with its own set of learned projections of queries, keys, and values.

6. Multi-Head Latent Attention (MLA) -> DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model (2405.04434)
Extends MHA by incorporating a latent space where attention heads can dynamically learn different latent factors or representations.

7. Memory-Based attention -> End-To-End Memory Networks (1503.08895)
Involves an external memory and uses attention to read from and write to this memory.

See other types in the comments 👇
  • 1 reply
·