Harsh .

📰 Check out this article by Akmal Chaudhri, our Technical Evangelist, where we'll explore various techniques for loan approvals, using models like Logistic Regression and BERT, and applying SHAP and LIME for model interpretation 👉 https://bit.ly/4ffgjD5 via DZone. 🕵️ We'll also investigate the potential of using LangChain for automating loan predictions with conversational AI. #AI #LLM #SingleStore

2

"Transformers from Large Language Models: A 100-minute lecture" The heart of LLMs like GPTs is transformers. If you have attempted to learn transformers, you must have realized that it is very hard. Each time I try to understand it further, I learn something new. At Vizuara, we wanted to create a comprehensive webinar series on transformers that will serve as the go-to resource for anyone who wishes to learn transformers, including its implementation. We have hosted a 100-minute lecture on our YouTube channel: https://lnkd.in/g2GC938P We have covered the following points: 1️⃣ History of Large Language Models (LLMs) 2️⃣ What are transformers? 3️⃣ Intuition behind transformers 4️⃣ Transformer architecture 5️⃣ NanoGPT 6️⃣ Applications of transformers for LLMs 7️⃣ Building awesome hands-on projects! Here is the link to the lecture The amount of blood, sweat, and research that went into making an almost beginner-friendly workshop was enormous. All credit to Sahil for that. Your work has been very inspirational. We strongly believe that this lecture will tremendously benefit you if you wish to learn about LLMs, transformers, attention mechanisms, the intuition behind positional encoding, etc. in detail.

48

2 Comments

🚀 Bengaluru-based Conversational AI Startup Gnani AI Raises $3M 💰 Gnani AI, India's first voice-first small language model (SLM) for vernacular languages, has secured $3M in funding from tech holding company Info Edge. The investment will fuel the startup's expansion plans. Key Highlights: • Gnani AI is building a series of voice-based SLMs, trained on millions of hours of proprietary audio datasets and billions of conversations in 12 Indian languages • The startup has over 100 customers in banking, financial services, insurance, telecom, automotive, and healthcare industries • Gnani AI's models run on the edge, reducing costs and enabling quick fine-tuning based on enterprise needs • The startup specializes in creating customized models for individual companies, adding real value to their data CEO Ganesh Gopalan emphasizes the importance of multimodal models, focusing on voice and text fusion. By taking their models to enterprises and helping them build on top of it, Gnani AI is revolutionizing the conversational AI landscape in India. #ConversationalAI #VoiceFirst #IndianLanguages #Funding #Expansion

12

1 Comment

Learning and Exploring Transformers at IIT Kharagpur's AI4ICPS Program After building a strong foundation in NLP and reinforcement learning, I’m now venturing into the fascinating world of transformers. The deeper I go, the more exciting it becomes! Here's what I’ve learned so far: Key Learnings: Understanding the Transformer Architecture: How transformers differ from RNNs and CNNs by using self-attention mechanisms to handle sequential data. Self-Attention Mechanism: Exploring how transformers focus on different parts of the input data simultaneously, making them incredibly efficient for both text and image processing tasks. Applications in NLP: Learning how transformers power state-of-the-art models like BERT and GPT, revolutionizing language models and tasks like translation, summarization, and sentiment analysis. Scalability and Efficiency: Understanding the scalability of transformers for large datasets and their ability to handle long sequences without losing context. Future Prospects: How transformers can be applied beyond NLP into areas like vision (Vision Transformers), reinforcement learning, and more. The IIT Kharagpur AI4ICPS Program continues to challenge and inspire me, and with each new topic, I’m more excited about the limitless applications of AI. I am grateful for the stellar guidance and encouragement from the professors. I look forward to exploring this horizon even more, as AI continues to evolve, and I can’t wait to dive deeper into the world of transformers and beyond! Resourcelink:https://lnkd.in/d6k2jg74 #AI4ICPS #Transformers #MachineLearning #Gratitude #ExcitedToLearnMore #IITKharagpur #AIJourney

4

Question : Sampling Techniques : What are they❓ As we saw recently in exit polls on Indian elections, choosing samples from a population can have a significant impact on predictions. #AI enthusiasts need to have a solid understanding of statistical sampling techniques. Statistical sampling is essential for AI product managers because it helps them: 1️⃣ Understand the Target Population: Accurate sampling ensures that the data used to train and evaluate AI models is representative of the target population, reducing the risk of biased or skewed results. 2️⃣ Optimize Data Collection: Sampling techniques can help AI product managers determine the appropriate sample size and sampling method, ensuring efficient and cost-effective data collection. 3️⃣ Validate Model Performance: Sampling is crucial for testing and validating AI models, as it allows for the creation of representative test sets that accurately reflect the real-world scenarios the model will encounter. AI enthusiasts should be aware of the different types of sampling methods, including: 🔺 Probabilistic Sampling Techniques: methods where randomisation is used instead of deliberate choice. 👉 Simple Random Sampling: Each member of the population has an equal chance of being selected. 👉Stratified Sampling: The population is divided into subgroups (strata), and samples are drawn from each stratum. 👉Cluster Sampling: The population is divided into clusters, and a random sample of clusters is selected. 👉Systematic Sampling: Every nth member of the population is selected, starting from a random point. 🔺 Non-Probabilistic Sampling Techniques: methods where some selection criteria exists 👉Convenience Sampling: Selecting participants based on their availability and accessibility. 👉Quota Sampling: Selecting participants to match predetermined proportions in the population. 👉Purposive Sampling: Selecting participants based on specific characteristics or criteria. 👉Snowball Sampling: Selecting participants through referrals from initial participants. The choice of sampling method depends on the specific goals of the AI project, the available resources, and the characteristics of the target population. Choosing the wrong sampling technique can lead to biased results, skewed data, and ultimately, the development of AI models that fail to perform well in real-world scenarios. 💡 Quick Tip: When selecting a sampling technique, consider the diversity and representativeness of the target population, the level of precision required, and the resources available for data collection.  #AI #ArtificialIntelligence #productmanagement #productmanager #DataScience 

7

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

555

14 Comments

May we all get the superpower to work with rich datasets📊 PS: Our team wrote a blog post on ‘How to build ML models?’ Do give it a read. Link here: https://lnkd.in/gF6nZ3gM

13

If we’ve a rich dataset, da da da da da, da da da da da da!  See all the insights we'd bring, no analysis could ever be boring. 'Cause we'd have all the data in the world! We’d have power to analyze, predict, and innovate, fueled by the wealth of information at our fingertips.  From market trends to customer behavior, every data point holds the potential for transformation. Check out our datakulture team’s latest blog post by Apoorva Grover on 'How to build ML models?' ⬇️ #Data #MachineLearning #BlogPost #ML #MLModel #DataLake #CloudApplications #sensor #IoT #RDBMS #MongoDB

11

Shoutout to Uttam Kumar, our Blogger of the Week! 🎉 In his latest blog, Uttam dives deep into Linear Discriminant Analysis (LDA) – a classic yet powerful technique for classification and feature extraction in machine learning. LDA finds the perfect balance by maximizing the separation between classes while minimizing within-class variance, making it ideal for applications like image and text classification, DNA analysis, and face recognition. Through Uttam's blog, explore the assumptions, advantages, and limitations of LDA and discover why it remains a go-to tool for reducing dimensionality and selecting key features. Read the complete blog (Link in the comment below)

3

1 Comment

When learning about machine learning, it's easy to get confused by algorithms that sound alike but serve entirely different purposes. Two such algorithms are K-Nearest Neighbors (KNN) and K-Means Clustering. While they both involve the concept of “K” and deal with proximity, that’s pretty much where their similarities end. Let’s dive into the differences, how each algorithm works, and when to use them, so you never mix up these two K’s again! Link to blog - https://lnkd.in/gBknwBwp #Machinelearning #datascience #ai #techexplained #InsideTheBlackBox

14

2 Comments

Thrilled to share that 2️⃣ / 2️⃣ of our works have been accepted EMNLP'24. 1️⃣. CorrSynth - A Correlated Sampling Method for Diverse dataset Generation from LLMs. (accepted at EMNLP'24 Main) The work is primarily lead by Abhishek Divekar and Suhas S Kowshik where we introduce a novel method to perform correlated sampling from LLMs to improve the distillation performance of student models. Kudos to both of them for their outstanding work! 2️⃣. PEARL: Preference Extraction with Exemplar Augmentation and Retrieval with LLM Agents (accepted at EMNLP'24 Industry Track) In this work, we propose a multi-agent framework leveraging the collaboration between large language models for providing product recommendations to customers in a conversational setting. Big thanks to Akshay Jagatap, Vinayak Puranik and Anirban Majumder for their immensely valuable contributions! Looking forward to presenting our works in person at the conference. See you in Miami, Florida 🌊 🛫 #EMNLP #ML #Research #LLM #NLP

96

Did you know - bad Statistical inference can derail your MMM project? After all the hard work of collecting the data, building the models, the last thing you would want is faltering at the model inference stage. Read on to know the common misinterpretations of MMM outputs in this substack post. https://lnkd.in/gcn-2qmt

6

82% MMLU and ~30x cheaper than GPT4o(~89%). This is amazing #gpt4omini can be the go-to model for many production use cases. We are in for an exciting next few months :) #GenAI #OpenAI #physicswallah

57

Excited to share our interactive BlogApp on Generalized Linear Models (GLMs)! In collaboration with Venkatachalam Subramanian Periya Subbu, Satya Lasya N, and Pooja Baralu Umesh, we've developed an intuitive tool that makes understanding GLMs both engaging and accessible. If you are an aspiring Data Scientist, Actuary, Statistician, Economist, Epidemiologists or an Engineer, you definitely need to check it out at: https://lnkd.in/gMqf3M5Y View the source code: https://lnkd.in/g9HUm_7r Special thanks to Professor Cody Carroll for the guidance throughout this project. Let's discuss GLMs! What's your experience with these powerful statistical tools? Share your thoughts below. #DataScience #Statistics #MachineLearning #GLM #Analytics #Programming #USF #MSDS

34

2 Comments

🔍 Discover the Future of Car Damage Detection with CarVigilance.AI! 🚗🔍 🌟 1: CarVigilance360 🌟 - Harness the power of Google Vit Transformer Beit for unparalleled car damage detection accuracy. (Beit model is trained using MLOps tool MLflow) - Enjoy live instance prediction and seamless batch prediction capabilities. - Detects 6 classes including Crack, Scratch, Tire Flat, Dent, Glass Shatter, and Lamp Broken with precision. - Timeline in Video: 00:00-03:26 🛡️ 2: DamageVigilance360 🛡️ - Experience rapid and efficient car damage detection using YOLOv8 technology. (YOLOv8 model is trained using MLOps tool Wandb.ai) - Benefit from live instance predictions and convenient batch prediction options. - Detects damages across seven classes including Bonnet, Bumper, Dickey, Door, Fender, Light, and Windshield. - Timeline in Video: 03:27-06:52 🎥 3: DamageDetect360 🎥 - Redefine car damage video prediction with YOLOv8 technology. (YOLOv8 model is trained using MLOps tool Wandb.ai) - Enjoy live instance predictions and seamless batch prediction capabilities. - Identify damages across seven classes including Bonnet, Bumper, Dickey, Door, Fender, Light, and Windshield for enhanced documentation and analysis. - Timeline in Video: 06:53-13:38 🔍 Applications: - 📈 Streamline Insurance Claims Processing - 🚗 Enhance Fleet Management - 🛠️ Ensure Thorough Used Car Inspection - 🚔 Aid in Accident Investigation 💡 CarVigilance's suite of solutions ensures enhanced accuracy, efficiency, and reliability for various automotive applications. 🎥 Please watch the exciting video showcasing every component of CarVigilance.AI! 🔗 Don't miss out! Explore the future of car damage detection with CarVigilance.AI. #AI #CarDamageDetection #Innovation #AutomotiveTechnology #artificialintelligence #datascientist #llm #llmops #aicommunity #beit #google #yolo #yolo8 #objectdetection #imageclassification #mlops #wandb #mlflow #machinelearning #machinelearningengineer #computervision #deeplearning #deeplearningai #mlcommunity #datascience #streamlit #instance #batchprocessing #endtoendsolutions #ai #aiapplications #transformers #transformermodels #webapplication

22

9 Comments

Graphs are important in representing complex relationships in various domains like social networks, knowledge graphs, and molecular discovery. Alongside topological structure, nodes often possess textual features providing context. Graph Machine Learning (Graph ML), especially Graph Neural Networks (GNNs), has emerged to effectively model such data, utilizing deep learning’s message-passing mechanism to capture high-order relationships. With the rise of Large Language Models (LLMs), a trend has emerged, integrating LLMs with GNNs to tackle diverse graph tasks and enhance generalization capabilities through self-supervised learning methods. The rapid evolution and immense potential of Graph ML pose a need for conducting a comprehensive review of recent advancements in Graph ML. #neuralnetworks #artificialintelligence #ai #graphneuralnetworks #llms #generativeai #deeplearning #machinelearning

3

1 Comment

"Transformers: The Heart of LLMs" The heart of LLMs like GPTs is transformers. If you have attempted to learn transformers, you must have realized that it is very hard. Each time I try to understand it further, I learn something new. At Vizuara, we wanted to create a comprehensive webinar series on transformers that will serve as the go-to resource for anyone who wishes to learn transformers, including its implementation. Sahil P., me, Rajat Dandekar and Raj Abhijit Dandekar have organized this lecture where you will; learn to train LLMs from scratch. You will also build awesome hands-on projects in this lecture. Transformers were introduced in the 2017 paper: "Attention is all you need". This beautiful 15 page-paper is however very difficult to understand for most people. The singular goal of our lecture is to give a good idea about what exactly is a transformer, how is it a neural network, and how is it used in LLMs like ChatGPT. We cover the following points: 1️⃣ History of Large Language Models (LLMs) 2️⃣ What are transformers? 3️⃣ Intuition behind transformers 4️⃣ Transformer architecture 5️⃣ Applications of transformers for LLMs 6️⃣ Building awesome hands-on projects! The amount of blood, sweat, and research that went into making an almost beginner-friendly workshop was enormous. We strongly believe that this lecture will tremendously benefit you if you wish to learn about LLMs, transformers, attention mechanisms, the intuition behind positional encoding, etc. in detail. Watch the lecture here: https://lnkd.in/g-Fq28Dr

44