3 2 191

RedRedRed

RedSparkie

AI & ML interests

⛧ ART⛧

Recent Activity

replied to singhsidhukuldeep's post about 14 hours ago

It's always exciting to revisit Google's DCN paper—impractical but good! Deep & Cross Network (DCN) - a groundbreaking approach to click-through rate prediction that's revolutionizing digital advertising! Key Innovation: DCN introduces a novel cross-network architecture that automatically learns feature interactions without manual engineering. What sets it apart is its ability to explicitly model bounded-degree feature crossings while maintaining the power of deep neural networks. Technical Deep Dive: - The architecture combines a cross network with a deep network in parallel. - The cross network performs automatic feature crossing at each layer. - The embedding layer transforms sparse categorical features into dense vectors. - Cross layers use a unique formula that enables efficient high-degree polynomial feature interactions. - Memory-efficient design with linear complexity O(d) in the input dimension. Performance Highlights: - Outperforms traditional DNN models with 60% less memory usage. - Achieved 0.4419 logloss on the Criteo Display Ads dataset. - Consistently performs better than state-of-the-art models like Deep Crossing and Factorization Machines. - Exceptional performance on non-CTR tasks like Forest Covertype (97.40% accuracy). Under the Hood: - Uses embedding vectors of dimension 6 × (category cardinality)^1/4. - Implements batch normalization and the Adam optimizer. - The cross network depth determines the highest polynomial degree of feature interactions. - An efficient projection mechanism reduces cubic computational cost to linear. - Parameter sharing enables better generalization to unseen feature interactions. Key Advantages: 1. No manual feature engineering required. 2. Explicit feature crossing at each layer. 3. Highly memory-efficient. 4. Scalable to web-scale data. 5. Robust performance across different domains. Thoughts on how this could transform digital advertising?

liked a Space about 14 hours ago

openfree/Tarot

Reacted to merve's post with 👀 about 14 hours ago

Apple released AIMv2 🍏 a family of state-of-the-art open-set vision encoders https://huggingface.co/collections/apple/aimv2-6720fe1558d94c7805f7688c > like CLIP, but add a decoder and train on autoregression 🤯 > 19 open models come in 300M, 600M, 1.2B, 2.7B with resolutions of 224, 336, 448 > Load and use with 🤗 transformers

View all activity

Organizations

RedSparkie's activity

replied to singhsidhukuldeep's post about 14 hours ago

Is there any update on this field of research? Not very keen on this, but I know a friend who'd like to know 😅.

liked a Space about 14 hours ago

Running

🌍

Tarot

Reacted to merve's post with 👀 about 14 hours ago

Post

411

Apple released AIMv2 🍏 a family of state-of-the-art open-set vision encoders
apple/aimv2-6720fe1558d94c7805f7688c
> like CLIP, but add a decoder and train on autoregression 🤯
> 19 open models come in 300M, 600M, 1.2B, 2.7B with resolutions of 224, 336, 448
> Load and use with 🤗 transformers

Reacted to cfahlgren1's post with ❤️ 2 days ago

Post

2816

You can clean and format datasets entirely in the browser with a few lines of SQL.

In this post, I replicate the process @mlabonne used to clean the new microsoft/orca-agentinstruct-1M-v1 dataset.

The cleaning process consists of:
- Joining the separate splits together / add split column
- Converting string messages into list of structs
- Removing empty system prompts

https://huggingface.co/blog/cfahlgren1/the-beginners-guide-to-cleaning-a-dataset

Here's his new cleaned dataset: mlabonne/orca-agentinstruct-1M-v1-cleaned