Uddipto Dutta

Another great talk from the PyData London 2024 - Backtesting and error metrics for modern time series forecasting by Kishan Manani Backtesting is the time series forecasting equivalent to the machine learning cross-validation approach for training and testing models. https://lnkd.in/g-DWgqmB #timeseries #forecasting #machinelearning #python

46

5 Comments

I have been asked by many #datascience , #aiml #professional and #enthusiast , What is the benefit of getting a Master Degree from premiere institute. I did my Master from Indian School of Business (AMPBA) and I feel fortunate to be the part of this Journey and I can list out some of the reasons below. 1. Quality of Education: Premier institutes are known for their excellent faculty, infrastructure, and academic resources. They provide high-quality education that equips students with the necessary knowledge, skills, and practical exposure required for their chosen profession. 2. Industry Recognition: Degrees and certifications from premier institutes are highly valued and recognized by employers and organizations. Graduates from such institutes are often sought after due to the rigorous training and qualifications they possess. 3. Networking Opportunities: Premier institutes offer excellent networking opportunities, allowing students to interact with industry professionals, attend seminars, and participate in events. These connections can be invaluable for future career prospects and professional growth. 4. Specialized Expertise: Premier institutes often have specialized programs or concentrations in specific fields, allowing students to gain in-depth knowledge and expertise in their area of interest. This specialized knowledge can give them a competitive edge in the job market. 5. Skill Development: Premier institutes emphasize not only theoretical knowledge but also practical skill development. They provide opportunities for internships, projects, and hands-on training, which help students develop essential skills required in their respective professions. 6. Personal Growth: The challenging academic environment and exposure to diverse perspectives at premier institutes foster personal growth, critical thinking, and problem-solving abilities, which are invaluable assets in any professional field. 7. Career Advancement: A degree or certification from a premier institute can open doors to better job opportunities, higher salaries, and faster career advancement. Employers often recognize the value of education from respected institutions. 8. Reputation and Prestige: Attending a premier institute carries a certain level of prestige and reputation, which can be beneficial for both personal and professional growth. It can enhance an individual's credibility and standing in their chosen field. While the investment in professional education from a premier institute may be substantial, the potential benefits in terms of knowledge, skills, networking opportunities, and career prospects often make it a worthwhile investment for individuals seeking professional growth and success. I am fortunate to meet professors like vijaya marisetty Subodha Kumar Manish Gupta Shailesh Kumar Niyati Chhaya to name a few. Thanks to BNY Mellon for sponsored me. Follow Bijan Dash for great insight and help. ISB Institute of Data Science (IIDS)

29

5 Comments

Summary of the recently concluded test match. https://lnkd.in/g6hZNruW #cricketanalytics #cricketdata #cricket #sportsanalytics

13

🌟 Retrieval-Augmented Generation (RAG) is truly a game-changer in the AI landscape! By seamlessly combining retrieval-based and generative models, RAG architecture enhances both the accuracy and relevance of AI outputs. The detailed process involving chunking, embedding, and vector search ensures that responses are not only precise but also contextually rich. This innovative approach is particularly beneficial in providing enhanced relevance, improved accuracy, and versatility across various domains. RAG is setting a new standard for intelligent systems, making AI interactions more informed and reliable. #AI #MachineLearning #RAG #ArtificialIntelligence #TechInnovation #DataScience #VectorSearch #LLM #Embeddings #GenAI 🚀🤖📚

2

🚀 Exploring MLFlow: Simplifying the Machine Learning Lifecycle 🚀 Machine Learning development can be complex, involving multiple steps from data preparation to model deployment. That's where MLFlow comes in, offering a comprehensive platform to manage the entire ML lifecycle. What is MLFlow? 🤔 MLFlow is an open-source platform designed to streamline the machine learning lifecycle, including experimentation, reproducibility, and deployment. It provides a set of tools to manage your ML projects efficiently. Key Features of MLFlow: Tracking 📝 Experiment Tracking: MLFlow tracks and records experiments, capturing parameters, metrics, and artifacts (like models). This makes it easy to compare different runs and choose the best performing model. Visualization: Visualize the performance of various experiments using interactive plots and dashboards. Projects 📁 Standardized Format: MLFlow Projects provide a standardized way to package your code, ensuring consistency and reproducibility. Dependency Management: Define dependencies in a conda.yaml file, ensuring the environment is consistent across different runs. Models 🤖 Model Packaging: MLFlow Models offer a standard format for packaging machine learning models. This makes it easy to deploy models across various platforms. Deployment Options: Deploy models to multiple platforms such as AWS SageMaker, Azure ML, or even as a REST API using MLFlow's built-in support. Registry 📜 Model Registry: The model registry allows you to store, annotate, and manage models in a central repository. Track model versions, stage transitions (e.g., staging to production), and lineage. Benefits of Using MLFlow: Consistency: Standardizes the ML lifecycle, ensuring consistency in how models are built, trained, and deployed. Reproducibility: Ensures experiments are reproducible by capturing all relevant information (code, data, configs). Collaboration: Facilitates collaboration among team members by providing a central platform for managing ML workflows. Scalability: Easily scale your ML projects by leveraging MLFlow's integration with various cloud platforms and deployment tools. Why MLFlow Matters in Today’s AI Landscape 🌐 In a world where AI and ML are driving innovation, MLFlow stands out as a crucial tool for data scientists and ML engineers. By simplifying the complex processes involved in ML development, it enables teams to focus on building better models and driving impactful results. Whether you’re experimenting with different algorithms, tracking model performance, or deploying models to production, MLFlow has got you covered. Embrace MLFlow to enhance your ML workflows and stay ahead in the AI race. 🔗 Dive deeper into MLFlow and transform your machine learning workflows today! #MachineLearning #MLFlow #AI #DataScience #ModelDeployment #OpenSource #MLOps #TechInnovation #AItools #Productivity #Efficiency https://lnkd.in/gP_DVM-5

6

1 Comment

🌟 What an exciting exploration into accelerating text generation for large language models! 🚀 Your research is paving the way for faster and more responsive AI systems, opening up new possibilities for real-time applications. Speculative Decoding, Early Exiting Mechanisms, and Non-Autoregressive Methods are fascinating techniques that promise significant speedups in text generation while maintaining quality. It's inspiring to see collaboration between leading institutions like MIT and Columbia University driving innovation in AI efficiency. This paper is a valuable resource for researchers and practitioners alike, shaping the future of AI technology. Can't wait to delve into the full details and witness the impact of these cutting-edge techniques firsthand! 🧠✨ #AIResearch #TextGeneration #Innovation #MIT #ColumbiaUniversity #TechAdvancement 📚🔬

9

3 Comments

For hyperparameter tuning hyperopt was the go to package. I recently learnt that the open-source package is no longer maintained. Microsoft and Databricks encourage the use of optuna for hyper parameter optimisation. MLflow have created this awesome tutorial to get you started using Databricks and Optuna.

11

Exploring Key Features of LLaMA 3.1: Next-Level Language Model Advancements LLaMA (Large Language Model Meta AI) 3.1 brings several enhancements and innovations to the world of large language models. Here’s a detailed look at the key features of LLaMA 3.1 and how they advance the capabilities of language models: 🔍 Key Features of LLaMA 3.1: Enhanced Model Architecture: Improved Transformer Design: LLaMA 3.1 features an upgraded transformer architecture that enhances its ability to understand and generate complex text, leading to more nuanced and coherent outputs. Increased Model Capacity: With more parameters compared to previous versions, LLaMA 3.1 offers improved performance and accuracy in various NLP tasks. Advanced Training Techniques: State-of-the-Art Data Utilization: LLaMA 3.1 leverages a broader and more diverse dataset for training, ensuring the model has a more comprehensive understanding of language and context. Refined Training Algorithms: Incorporates the latest advancements in training algorithms to optimize learning and reduce overfitting, resulting in more reliable performance. Enhanced Contextual Understanding: Longer Context Windows: The model can process and remember longer contexts, allowing it to generate more contextually relevant and coherent responses over extended conversations. Better Handling of Ambiguities: Improved mechanisms for managing ambiguous or complex queries, leading to more accurate and relevant responses. Optimized Performance: Faster Inference: LLaMA 3.1 is optimized for faster inference times, improving its efficiency and responsiveness in real-time applications. Reduced Resource Consumption: Enhanced model efficiency means lower computational costs and resource usage, making it more accessible for deployment at scale. Robust Fine-Tuning Capabilities: Customizable for Specific Tasks: The model supports advanced fine-tuning techniques, allowing users to tailor LLaMA 3.1 for specific applications or industry needs with greater ease. Enhanced Transfer Learning: Improved capabilities for transferring knowledge from one domain to another, enabling better performance on niche tasks. Enhanced Safety and Bias Mitigation: Ethical AI Guidelines: Incorporates updated guidelines for reducing biases and ensuring ethical use of AI, improving the model’s fairness and inclusivity. Robust Filtering Mechanisms: Enhanced mechanisms to filter out harmful or inappropriate content, ensuring safer interactions. 🌟 Applications of LLaMA 3.1: Conversational AI: Improved performance in chatbots and virtual assistants, offering more natural and engaging interactions. Content Creation: Generates high-quality, contextually relevant content for various applications, from marketing to creative writing. #LLaMA3_1 #AI #MachineLearning #NaturalLanguageProcessing #DataScience #LanguageModels #TechInnovation #ArtificialIntelligence #ModelAdvancements #NLP

1

Fine-tune your SLM (Gemma-2B) for English-Hindi translation on Kaggle! The Kaggle notebook covers data gathering, prompt template development, fine-tuning, and evaluation. Get started here: https://lnkd.in/gWNEpvm2

12

Impressive work! 📚 The detailed notebooks in your repository offer a fantastic resource for anyone diving into Retrieval Augmented Generation. From indexing pipelines to RAG evaluation, it’s great to see such a comprehensive guide for beginners. The inclusion of practical examples and advanced strategies makes this a valuable tool for learning and implementing RAG systems. Looking forward to exploring the upcoming chapters! #RAG #RetrievalAugmentedGeneration #MachineLearning #AI #DataScience #TechEducation #ManningPublications #OpenSource

1

Which button to press to build PD, LGD, EAD?   When I see how technologies are developing in neighboring departments of Sber, this question arises in my head. Of course, modeling in finance is automated mostly: - data flows, their storage and processing; - running statistical packages with building models and assessing quality; - implementation and monitoring; - etc.   But it seems that human participation in this area will still remain significant. At least because:  - there are regulatory issues that can be interpreted in a wide range; - new products appear that create new data flows - shifts and shocks in economies that break previous ideas about the best risk drivers in models - and much more that you can add.   Of course, technology and AI help to automate and simplify a lot. But they also create ever larger data flows and increasingly change the landscapes to which they were previously applied.

23

2 Comments

I call this time series model the ARIMA Killer!! Dramatic hooks gets us more clicks right? Anyways, for people who are into time series, do read this. I am doing a series (has no relation with pandas Series, nor time series, HAHAHA, {lame}) in which I would be covering somewhat latest developments in time series forecasting/analysis, and some of the common and/or advanced time series tasks that the Internet Gurus won't teach you. I am excited to announce that I have successfully written another blog🚀💫 (sarcasm) #timeseries

8

2 Comments

What is RAG ? The RAG (Retrieval-Augmented Generation) concept is a recent development in natural language processing (NLP) that combines retrieval-based and generative approaches to improve language understanding and generation tasks. RAG models leverage the strengths of both retrieval and generation models to achieve better performance in tasks such as question answering, summarization, and dialogue generation. Here's an overview of the RAG concept and how it works: Retrieval-Based Models: Traditional retrieval-based models use a search mechanism to retrieve relevant information from a large corpus of documents or passages. These models are effective at finding exact or closely related matches to a given query but may struggle with generating novel or diverse responses. Generative Models: Generative models, such as language models (e.g., GPT, BERT), can generate new text based on the input they receive. These models have the advantage of producing diverse and contextually relevant responses but may lack the ability to retrieve specific information from external knowledge sources. The RAG concept combines these two approaches by integrating a retriever component with a generative model. Here's how it typically works: Retriever Component: The retriever component retrieves relevant passages or documents from a knowledge source (e.g., a large text corpus, a knowledge graph) based on the input query or context. This retrieval is typically based on keyword matching, semantic similarity, or other information retrieval techniques. Generative Model: The retrieved passages are then used as context or input for a generative model, such as a language model, which generates a response or output based on the retrieved information. The generative model may fine-tune its output based on the retrieved context to ensure relevance and coherence. By combining retrieval-based and generative approaches, RAG models can leverage the comprehensive knowledge available in large text corpora while still being able to generate diverse and contextually relevant responses. This hybrid approach has shown promising results in various NLP tasks, including question answering, summarization, and dialogue generation. The RAG concept has been explored in recent research papers, and variants of RAG models have been proposed with different architectures and training strategies. As NLP research continues to advance, RAG models are expected to play an increasingly important role in improving the performance of language understanding and generation systems.

5

 Dear LinkedIn Family, We are looking for Senior Data Scientist for Pune Location. #DataScientist LLM Architecture: Good understanding of the architecture underlying large language models, such as Transformer-based models and their variants. Design and implement deep learning model architectures using PyTorch. #LLM #PyTorch #pytorch Language Model Training and Fine-Tuning: Experience in training large-scale language models from scratch, as well as fine-tuning pre-trained models on domain data. Data Preprocessing for NLP: Skilled in preprocessing textual data, including tokenization, stemming, lemmatization, and handling of different text encoding. Transfer Learning and Adaptation: Proficiency in applying transfer learning techniques to adapt existing LLMs to new languages, domains, or specific business needs. Data Annotation and Evaluation: Skills in designing and implementing data annotation strategies for training LLMs and evaluating their performance using appropriate metrics. Scalability and Deployment: Experience in scaling LLMs for production environments, ensuring efficiency and robustness in deployment. Model Training, Optimization, and Evaluation: Evaluate the performance of PyTorch models using appropriate metrics and techniques like cross-validation, holdout sets, or online evaluation. This encompasses the complete cycle of training, fine-tuning, and validating language models. You will be designing and adapting LLMs for use in virtual assistants, Information retrieval and extraction etc. Experimentation with Emerging Technologies and Methods: Actively exploring new technologies and methodologies in language model development, including experimental frameworks and software tools. LLM Alignment: Understanding of algorithms like DPO, PPO, KPO, RLHF and using it for guardrails. AI Data Retrieval: Data retrieval from unstructured data, extract key value pairs using techniques like donut, layoutLM, table transformers. Analyze data and build EDAs to identify data patterns Hands-on and strong understanding of concepts in Deep Learning and NLP Proficient in TensorFlow and similar libraries.   Required Qualifications 5+ years of hands-on experience in developing and deploying Large Language Models, and Machine learning and working with Pytorch. A thorough understanding of machine learning, particularly deep learning techniques, including knowledge of neural network architectures, training methods, and optimization algorithms. Proficiency in AI technology, Python, including experience with NLP libraries (e.g., Hugging Face Transformers, NLTK, spaCy), text classification. Experience with frameworks: PyTorch, or Tensorflow. Experience with cloud services (AWS, Azure) and ML deployment tool Docker Familiarity with model fine-tuning and optimization techniques for LLMs. Proven track record of innovative solutions in the field of LLMs. Strong communication skills, with the ability to explain complex AI concepts to non-expert audiences.

4

1 Comment

Prometheus 2: open-source Language Model (LM) evaluation! Researchers have introduced Prometheus 2, a powerful open-source LM specifically designed for evaluating other LMs. This addresses growing concerns about the transparency, controllability, and affordability of relying solely on proprietary LMs like GPT-4 for evaluation purposes. Challenges with Existing Open-Source Evaluator LMs: *  Discrepancies with Human Judgement: Scores generated by these models often deviate significantly from human evaluations. *  Limited Evaluation Formats: They lack the flexibility to handle both direct assessments and pairwise rankings, which are the two most common evaluation methods. *  Restricted Evaluation Criteria: Existing models focus on general attributes like helpfulness and harmlessness, without the ability to incorporate custom criteria. Prometheus 2: A Game Changer *  Alignment with Human Judgements: Prometheus 2 demonstrates a remarkable ability to closely mirror human evaluations, as well as those of GPT-4. *  Versatile Evaluation Formats: It effectively handles both direct assessments and pairwise rankings. *  Customizable Evaluation Criteria: Users can define specific criteria to guide the evaluation process, allowing for greater control and precision. Results: Across various benchmarks, Prometheus 2 achieves the highest correlation and agreement with human judgements and proprietary LMs among all tested open-source evaluator LMs. Open Access: The models, code, and data for Prometheus 2 are all publicly available, fostering transparency and collaboration within the research community. Link to access the resources: https://lnkd.in/gudkqVyv Read more about the "Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models" in this research paper: https://lnkd.in/giW-rmRW #LanguageModels #LLM #AI #NLP #opensource #MachineLearning #LargeModels

26

The quantized version of a language model to perform text generation tasks in both Hindi and English. It's fine tuned aditi model on latest dataset release by sarvamai. https://lnkd.in/gvQ55Vd8 and other hindi datasets. Try out it out free on colab https://lnkd.in/gvbmBzSA model link: https://lnkd.in/gDKqSwtq. #huggingface #datasets #tuningmodel #ML #machinelearning #AI

1

[playground] Quantile Regression (with Keras & Scikit-Learn) Informed decision-making is the cornerstone of effective business. Quantile regression is a technique for estimating the conditional quantiles of the response variable across values of the predictor variables, which is a powerful tool for making actionable insights. Application of Quantile Regression: - Based on distance (and other predictor variables), estimates delivery time (quantile) that covers (percentile)% on-time deliveries. Case study: (check link in my blog) In this tutorial, we will fit a quantile regression model with Keras & Scikit-Learn. https://lnkd.in/ejPSmNC3

26

The Buzz word every where is GenAI , LLM's and Multi models , lets discuss on use cases where its driven significant value and not just made life slightly easier for stake holders. Comment below and lets discuss. #genai #llm #datascience

6

6 Comments

Interesting research paper alert : https://lnkd.in/giwG6bnZ Been thinking about evaluators and can they be self taught ! Stumbled upon this research paper and here is a Quick read about this : This paper on "Self-Taught Evaluators" introduces a novel approach to improving large language model (LLM) evaluators without relying on human-annotated data. The authors present an iterative self-improvement scheme that generates synthetic training data, allowing the LLM-as-a-Judge to self-train by generating contrasting model outputs and reasoning chains. This iterative process enables the evaluator to produce more accurate judgments, resulting in continuous performance improvement without the need for expensive and potentially outdated human annotations. Key contributions and insights from the paper include: Self-Taught Iterative Process: The core innovation is the use of synthetic data to generate contrasting model responses, which the LLM-as-a-Judge then evaluates. Over iterations, the model self-trains on its own outputs, improving its judgment accuracy. Performance Gains: The self-taught method shows impressive results, improving the Llama-3-70B-Instruct model's accuracy on RewardBench from 75.4 to 88.7, outperforming other commonly used LLM evaluators like GPT-4. Synthetic Data Creation: Synthetic preference pairs are generated without human input by prompting the LLM to produce one high-quality response and one lower-quality response to a modified version of the original instruction. This method allows the model to self-annotate its own training data. Iterative Fine-Tuning: In each iteration, the model uses the judgments it generates to improve its ability to evaluate responses. As the model's accuracy increases, the quantity of correct training examples increases as well, driving further improvement. LLM-as-a-Judge: The paper emphasizes the growing trend of using LLMs not just as response generators but also as judges, especially for open-ended or complex instructions where human evaluation is costly and subjective. The LLM-as-a-Judge provides explainable reasoning chains alongside its judgments, which enhances interpretability. Generalization: The method shows strong generalization across different domains, including reasoning, coding, and other complex tasks, highlighting its flexibility and scalability. Overall, this work demonstrates a significant step forward in LLM-based evaluation by leveraging self-training techniques and synthetic data, which reduce dependency on human annotations and accelerate model development. Saylee Muley You might want to use this, I remember you trying to use an LLM to evaluate the results from LLMs. #generativeAI #LLMs #AI

7

5 Comments