Devansh Mody

Build your machine learning portfolio with our Python for Machine Learning: The Essential Starter Kit course, starting September 9. Register before August 12 and receive a 10 per cent early bird discount with code PMLEB10. This code must be applied at the time of registration and cannot be combined with other discounts or promotions. Perfect for professionals looking to advance into roles that include machine learning, this course is designed to introduce you to Python, a programming language known for its simplicity and readability. You will understand how Python can be used for machine learning tasks and learn to use its popular packages and libraries for data preparation. Learn more and register: https://lnkd.in/gz9wS_fp Mehrdad Pirnia Fuat Can Beylunioğlu Manda (Hongxiu) Li, Ph.D. #Python #Machinelearning

13

One good news: one of my research papers gets accepted in ICSE-2025 (research track). The title of the paper is “Ranking Relevant Tests for Order-Dependent Flaky Tests”. #ICSE2025, #LLM, #testing, #ottawa - #Canada

89

20 Comments

The next guest speaker in my LLM course is Ram Sriharsha, the CTO of Pinecone, who will talk about Retrieval Augmented Generation (RAG) on Monday October 28. ➡️ Register here: https://lu.ma/r7yokyvc Title: Knowledgeable Models Combine Retrieval with Generation: An Introduction to RAG Date: Monday October 28 from 1:45 PM to 3:15 PM ET Abstract: Large Language Models have emerged into mainstream over the last few years. While they have demonstrated some huge successes already, they have also had challenges with hallucinations, difficulty with dealing with new knowledge and in retrieving relevant, accurate knowledge for downstream tasks. In this talk, we will provide a brief overview of the problem, and discuss a promising approach to solving these problems through what is known as Retrieval Augmented Generation (RAG). Alongside, we will also introduce vector databases, what makes them different from traditional databases and how they fit into RAG. Bio: Dr. Ram Sriharsha is the CTO at Pinecone. At Pinecone, Ram is responsible for overseeing the company’s technical direction in both engineering and research. Prior to joining Pinecone, Ram held numerous senior positions at some of the most well-known companies in the tech industry. Most recently, he was Vice President of Engineering at Splunk. Before that, he was a product and engineering lead at Databricks for their unified analytics platform for genomics. Some years after receiving a PhD in Physics from the University of Maryland, Ram was a Principal Software Engineer and later a Principal Research Scientist at Yahoo. Supplementary Readings: ➡️ The original paper on RAG: "Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks" (https://lnkd.in/e_e56Y54) ➡️ Long context considerations: "Lost in the Middle: How Language Models Use Long Contexts" (https://lnkd.in/ehED53Fe) ➡️ Article on contextual RAG from Anthropic AI (https://lnkd.in/ehK4GwMc)

69

NiNo: A Novel Machine Learning Approach to Accelerate Neural Network Training through Neuron Interaction and Nowcasting Researchers from Samsung’s SAIT AI Lab, Concordia University, Université de Montréal, and Mila have introduced a novel approach known as Neuron Interaction and Nowcasting (NINO) networks. This method aims to significantly reduce training time by predicting the future state of network parameters. Rather than applying an optimization step at every iteration, as with traditional methods, NINO employs a learnable function to predict future parameter updates periodically. By integrating neural graphs—which capture the relationships and interactions between neurons within layers—NINO can make rare yet highly accurate predictions. This periodic approach reduces the computational load while maintaining accuracy, particularly in complex architectures like transformers. At the core of the NINO methodology lies its ability to leverage neuron connectivity through graph neural networks (GNNs). Traditional optimizers like Adam treat parameter updates independently without considering the interactions between neurons. NINO, however, uses neural graphs to model these interactions, making predictions about future network parameters in a way that reflects the network’s inherent structure. The researchers built on the Weight Nowcaster Networks (WNN) method but improved it by incorporating neuron interaction modeling. They conditioned NINO to predict parameter changes for the near and distant future. This adaptability allows NINO to be applied at different stages of training without requiring constant retraining, making it suitable for various neural architectures, including vision and language tasks. The model can efficiently learn how network parameters evolve by using supervised learning from training trajectories across multiple tasks, enabling faster convergence.... Read our article on this:https://lnkd.in/gSQFYtcG Paper: https://lnkd.in/g9rJ5JT2 GitHub Page: https://lnkd.in/gJPbT-kM

25

In this article, Akila S explains why validation is crucial in an ML pipeline and the 5 stages of machine learning validations:

9

Don’t forget to join us this Wed on July 3 for the monthly AI, Machine Learning and Computer Vision Meetup!  Register for the Zoom: https://lnkd.in/g6ym2fBm We have a great lineup of speakers including: * Performance Optimization for Multimodal LLMs - Neha Sharma from Ori Industries * Deep Dive: Responsible and Unbiased GenAI for Computer Vision - Daniel G. at Voxel51 * 5 Handy Ways to Use Embeddings, the Swiss Army Knife of AI - Harpreet Sahota 🥑 at Voxel51 #computervision #ai #artificialintelligence #machinevision #machinelearning #datascience #gpu

1

📄🎉 Thrilled to announce the publication of Hashini Gunatilake's latest paper on human aspects in software engineering! Her research delves into the intricate dynamics of developer-user interactions, shedding light on crucial insights for the field. Through a detailed systematic literature review (SLR) approach, she's reviewed findings from 46 primary studies, offering a comprehensive view of how human factors shape these interactions. From identifying key human aspects to proposing practical mitigation strategies, this paper equips both practitioners and researchers with valuable tools for improving software engineering practices. Read the paper here: https://lnkd.in/g-wud7R9 #HumanAspects #SoftwareEngineering #Research Monash Information Technology, John Grundy, Rashina Hoda, Ingo Mueller

15

2 Comments

Unlock the full potential of your Large Language Models (LLMs) with Intel® Extension for PyTorch (IPEX) and the Intel® LLM Library for PyTorch (IPEX-LLM). Download this whitepaper to explore the optimization of LLMs, including their performance, resource utilization, and response times in real-world applications. Link - https://intel.ly/3BBJ4ey

1

Sign up now for our Introduction to Causal Inference course, where Mulusew J. Gerbaba Associate Research Scientist – Impact Evaluation at APHRC will dive into the methods of causal inference using observational data. You'll explore topics like potential outcomes, DAGs and causal graphs, target trial emulation, matching techniques, managing confounding and bias, causal structure learning, and quasi-experimental methods. Don't miss this opportunity to acquaint yourself with modern causal modeling methodology. Register today! https://lnkd.in/dcMnHVzX #MentalHealthDataPrizeAfrica #MentalHealthAwareness #DataForChange

10

LlamaIndex + MLflow RAG contains a lot of parameters to tune, from chunking to indexing - everything affects downstream answer accuracy. It’s important to have a systematic approach to track and tune these parameters, and define the right eval metrics/dataset to evaluate changes. Check out Jino Rohit's video on experimenting with a LlamaIndex pipeline with MLflow for experiment tracking. https://lnkd.in/gyYXfyyb

554

14 Comments

Text chunks in retrieval may risk losing context. The below article introduces contextualizing each chunk using an LLM. The added cost and latency required for contextualizing is partially addressed through a lightweight LLM (haiku) and prompt caching. Along with other known techniques (BM25, reranking, etc.), a significant reduction in retrieval failure is achieved. Overall, a good article to read. https://lnkd.in/g_5fgAN8

10

Quantized embeddings offer significant advantages for NLP models, including reduced storage requirements, faster computations, lower energy consumption, and improved model interpretability. They are becoming increasingly important for enabling efficient and scalable NLP on resource-constrained devices and cloud-based applications. Read my latest article below

6

An underrated component of RAG evals is retrieval evals - is potentially more important than LLM evals! Some requirements for performing retrieval evals is 1) identifying the right retrieval metrics, and 2) having a unified dataset representation. This article by Ross Ashman takes you through tour of retrieval/ranking metrics (e.g. precision@K, NDCG, and more), and also shows you how to convert a dataset into the BEIR format in order to run these evals. Once retrieval evals is setup, run it over your LlamaIndex retrievers. https://lnkd.in/gfha8kiX

173

3 Comments

We developed deep learning integration and MDA for Stanford University! This case study shows how our software developer team visualized the limitations and designed a user-friendly interface for sensitive data management. 𝗧𝗵𝗲 𝗖𝗼𝗺𝗽𝗮𝗻𝘆: Stanford University is a millennium-old education center in California, popular for its contribution to research. They needed an Analyxus-based data tool to manage their biomedical sensory, clinical, single-cell, and other omics data. VISER X helped design a system to streamline the process securely. 𝗢𝘂𝗿 𝗔𝗽𝗽𝗿𝗼𝗮𝗰𝗵: We have observed complex data structures. It was needed to put data analysis capabilities in biomedical research, clinical diagnostics, and other scientific domains. Our developer team followed a series of approaches to implement deep learning algorithms for robust analysis. ✅ Made deep learning models ✅ Developed MDA method ✅ Redesigned the UI/UX ✅ Improved visualization tools ✅ Handled large datasets ✅ Completed QA check 𝗙𝗶𝗻𝗮𝗹 𝗥𝗲𝘀𝘂𝗹𝘁: Analyxus project achieved a success rate of 95% in meeting project objectives. The tool has been widely adopted in biomedical research institutions and clinical laboratories, contributing to advancements in understanding complex biological data and improving diagnostic capabilities Get in touch with VISER X and craft your own success story. ☎ 01842-088100 🌎 https://lnkd.in/gxJANNHF #StanfordUniversity #DataManagement #SoftwareDevelopment #UIUXDesign #BiomedicalResearch #CaseStudy

9

💡Blog Post Alert: Explainability (XAI) techniques for Deep Learning and limitations💡 As AI continues to transform industries, understanding how models make decisions is crucial. In our latest blog, we explore key explainability techniques for deep learning models, including visualization-based methods like Grad-CAM and distillation methods like LIME. While these tools help bridge the gap between complex AI systems and human understanding, challenges like computational complexity and data-specific limitations still remain. Check out Part I of our blog series to learn more about the current state of XAI and the road ahead for AI transparency. Stay tuned for Part II on the opportunities explainability can unlock! Read more 👉 https://lnkd.in/gzqY9pD2 #AI #ExplainableAI #MachineLearning #AITransparency #DeepLearning #AryaXAI

9