background

30 November 2024

avatar

Daniele Moltisanti

7 min

RAGCache: Enhancing Efficiency in Retrieval-Augmented Generation

Discover how RAGCache optimizes Retrieval-Augmented Generation by reducing latency and improving throughput, enabling more efficient AI applications

background

29 November 2024

avatar

Daniele Moltisanti

14 min

Why Conditional Data Permutations Are Essential for Accurate XAI Analysis

Learn why conditional data permutations are essential for accurate XAI. Discover how they solve the problem of correlation breakdown and improve variable importance and PDP analyses

background

28 November 2024

avatar

Daniele Moltisanti

9 min

Docling: Streamlining Document Processing for Generative AI Applications

Discover how Docling simplifies document processing for AI applications. Learn about its features, installation, usage, and practical benefits in AI model training

background

20 November 2024

avatar

Daniele Moltisanti

14 min

Meta Learning for Model Optimization: A Comprehensive Guide

Discover how meta-learning revolutionizes model optimization with a 3-step approach: featurizing meta-data, training a meta-learner, and searching for optimal models. Learn how this method automates AI efficiency

background

30 October 2024

avatar

Daniele Moltisanti

16 min

How to Optimally Sample Imbalanced Data Practical Guide

Learn how to handle imbalanced data in machine learning with a step-by-step guide. Discover optimal sampling techniques, pilot models, and unbiased likelihood correction for better model performance

background

11 October 2024

avatar

Daniele Moltisanti

19 min

KnockKnock: Automate Your Machine Learning Notifications with Ease

Automate machine learning notifications with KnockKnock, a Python library that integrates with Desktop, Telegram, Email, and Slack. Save time and monitor your training scripts efficiently

background

20 September 2024

avatar

Daniele Moltisanti

11 min

Microsoft Open-Sources BitNet: A 1-Bit LLM Framework Revolutionizing AI Efficiency

Microsoft open-sources BitNet, a 1-bit LLM framework that optimizes AI efficiency by reducing memory and energy demands. Learn how BitNet is transforming large language models

background

12 September 2023

avatar

Daniele Moltisanti

39 min

The Power of Synthetic Data: Enhancing AI Model

Unlock AI's potential with synthetic data. Explore GANs, VAEs, and Diffusion Models, code examples, and quality checks. Elevate your AI's performance!

background

12 April 2023

avatar

Daniele Moltisanti

8 min

Elevate Your Time Series Analytics with Temporal Fusion Transformer

Time series analysis made easy with Temporal Fusion Transformer. Discover its versatility and improve your decision-making process

background

24 March 2023

avatar

Marcello Politi

11 min

TensorFlow CNN for Multilabel Image Classification Task

TensorFlow CNN for Multilabel Image Classification Task

background

15 March 2023

avatar

Francesco Di Salvo

6 min

Contextualized Embeddings with ELMo

Discover the power of ELMo, the state-of-the-art deep-learning model that generates contextualized word representations for improved natural language processing tasks.

background

21 February 2023

avatar

Francesco Di Salvo

6 min

Increase your productivity with your own PyTorch template

Enhance productivity with a custom PyTorch deep learning pipeline. Streamline model experimentation, secure reproducibility, and tailor to your needs.

background

13 February 2023

avatar

Gabriele Cola

4 min

Why Software Engineering is important in Data Science

Software engineering is an important aspect of the data science field that helps to ensure the development of high-quality, scalable, and maintainable systems

background

02 February 2023

avatar

Daniele Moltisanti

5 min

Using Autoencoders for Anomaly Detection in Strong Unbalanced Datasets

Anomaly detection is a critical task in various domains such as fraud detection, network intrusion detection, and medical diagnosis. One of the main challenges in anomaly detection is dealing with strong unbalanced datasets, where the number of anomalous examples is significantly smaller than the number of normal examples.

background

24 January 2023

avatar

Matteo Villosio

7 min

Measure the distance between documents with cosine similarity

Discover Cosine Similarity in NLP: Outperforms Euclidean, ideal for sparse data. Learn about its computation, benefits, and use in document comparison

1 2
JoinUS