Kuldeep Singh Sidhu's picture
6 3

Kuldeep Singh Sidhu

singhsidhukuldeep

AI & ML interests

😃 TOP 3 on HuggingFace for posts 🤗 Seeking contributors for a completely open-source 🚀 Data Science platform! singhsidhukuldeep.github.io

Recent Activity

posted an update about 8 hours ago
posted an update 1 day ago
posted an update 3 days ago

Organizations

Posts 87

view post
Post
283
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?
view post
Post
993
Sorry judge, my lawyer hallucinated? 😂 If you get an AI lawyer, you would want it to be hallucination-free!

New @Stanford -@Yale research reveals surprising findings about leading AI legal research tools. Here's what you need to know:

>> Key Findings
The study tested LexisNexis (Lexis+ AI), Thomson Reuters (Westlaw AI & Ask Practical Law AI), and GPT-4, finding hallucination rates between 17-33% despite claims of being "hallucination-free".

>> Technical Deep Dive
The research evaluated these tools using Retrieval-Augmented Generation (RAG) architecture, which operates in two crucial steps:

1. Retrieval System:
- Uses neural text embeddings to capture semantic meaning
- Employs both lexical and semantic search mechanisms
- Implements document filtering and extraction
- Retrieves relevant legal documents from vast databases

2. Generation Pipeline:
- Processes retrieved documents alongside original queries
- Synthesizes information from multiple legal sources
- Generates responses based on retrieved context
- Includes citation verification mechanisms

>> Performance Breakdown:
- Lexis+ AI: 65% accuracy rate
- Westlaw AI: 42% accuracy rate
- Ask Practical Law AI: Over 60% incomplete answers

>> Why This Matters
This research exposes critical vulnerabilities in AI legal tools that lawyers increasingly rely on. It's essential for legal professionals to understand these limitations when incorporating AI into their practice.

models

None public yet

datasets

None public yet