Data Brew Season 2 Episode 7: Interpretable Machine Learning

Data Brew by Databricks

MP3•Pagina principale dell'episodio

30:28

Building a thriving business isn't always about rapid expansion. When should you hit the accelerator on growth, and when should you pump the brakes? Jannese and Austin are in Nashville, Tennessee to talk with Taku Zhou and Sibusiso Ajayi of TKZ Architecture LLC to explore this crucial entrepreneurial crossroads. The duo shares candid insights from their journey building TKZ Architecture, revealing the moments they knew it was time to scale – and importantly, when it wasn't. They discuss how they balanced the allure of growth against the need to strengthen their foundation through refined workflows, established protocols, and market positioning. Tune in as we unpack the strategic decision-making that goes into sustainable business expansion and learn the telltale signs that you're ready for growth and how to execute that transition successfully. Learn more about how QuickBooks can help you grow your business: QuickBooks.com See omnystudio.com/listener for privacy information.…

4 anni fa 37:07

For our second season of Data Brew, we will be focusing on machine learning, from research to production. We will interview folks in academia and industry to discuss topics such as data ethics, production-grade infrastructure for ML, hyperparameter tuning, AutoML, and many more.
What does it mean for a model to be “interpretable”? Ameet Talwalkar shares his thoughts on IML (Interpretable Machine Learning), how it relates to data privacy and fairness, and his research in this field.
See more at databricks.com/data-brew

42 episodi

#Databricks #Data Analytics #Apache Spark #Delta Lake #Machine Learning #Data Engineering #Artificial Intelligence #Tech #Data Science #Science #Lifestyle #Podcasting Education

Data Brew Season 2 Episode 7: Interpretable Machine Learning

Data Brew by Databricks

71 subscribers

published 4 anni fa

MP3•Pagina principale dell'episodio

42 episodi

#Databricks #Data Analytics #Apache Spark #Delta Lake #Machine Learning #Data Engineering #Artificial Intelligence #Tech #Data Science #Science #Lifestyle #Podcasting Education

Alle afleveringen

1
SWE-bench & SWE-agent | Data Brew | Episode 44 36:22

8 hours fa36:22

36:22

In this episode, Kilian Lieret, Research Software Engineer, and Carlos Jimenez, Computer Science PhD Candidate at Princeton University, discuss SWE-bench and SWE-agent, two groundbreaking tools for evaluating and enhancing AI in software engineering. Highlights include: - SWE-bench: A benchmark for assessing AI models on real-world coding tasks. - Addressing data leakage concerns in GitHub-sourced benchmarks. - SWE-agent: An AI-driven system for navigating and solving coding challenges. - Overcoming agent limitations, such as getting stuck in loops. - The future of AI-powered code reviews and automation in software engineering.…

1
Enterprise AI: Research to Product | Data Brew | Episode 43 38:03

7 giorni fa38:03

38:03

In this episode, Dipendra Kumar, Staff Research Scientist, and Alnur Ali, Staff Software Engineer at Databricks, discuss the challenges of applying AI in enterprise environments and the tools being developed to bridge the gap between research and real-world deployment. Highlights include: - The challenges of real-world AI—messy data, security, and scalability. - Why enterprises need high-accuracy, fine-tuned models over generic AI APIs. - How QuickFix learns from user edits to improve AI-driven coding assistance. - The collaboration between research & engineering in building AI-powered tools. - The evolving role of developers in the age of generative AI.…

1
Multimodal AI | Data Brew | Episode 42 42:14

10 giorni fa42:14

42:14

In this episode, Chang She, CEO and Co-founder of LanceDB, discusses the challenges of handling multimodal data and how LanceDB provides a cutting-edge solution. He shares his journey from contributing to Pandas to building a database optimized for images, video, vectors, and subtitles. Highlights include: - The limitations of traditional storage systems like Parquet for multimodal AI. - How LanceDB enables efficient querying and processing of diverse data types. - The growing importance of multimodal AI in enterprise applications. - Future trends in AI, including a shift from single models to holistic AI systems. - Predictions and "spicy takes" on AI advancements in 2025.…

1
Age of Agents | Data Brew | Episode 41 40:47

21 giorni fa40:47

40:47

In this episode, Michele Catasta, President of Replit, explores how AI-driven agents are transforming software development by making coding more accessible and automating application creation. Highlights include: - The difference between AI agents and copilots in software development. - How AI is democratizing coding, enabling non-programmers to build applications. - Challenges in AI agent development, including error handling and software quality. - The growing role of AI in entrepreneurship and business automation. - Why 2025 could be the year of AI agents and what’s next for the industry.…

1
Reward Models | Data Brew | Episode 40 39:58

28 giorni fa39:58

39:58

In this episode, Brandon Cui, Research Scientist at MosaicML and Databricks, dives into cutting-edge advancements in AI model optimization, focusing on Reward Models and Reinforcement Learning from Human Feedback (RLHF). Highlights include: - How synthetic data and RLHF enable fine-tuning models to generate preferred outcomes. - Techniques like Policy Proximal Optimization (PPO) and Direct Preference Optimization (DPO) for enhancing response quality. - The role of reward models in improving coding, math, reasoning, and other NLP tasks. Connect with Brandon Cui: https://www.linkedin.com/in/bcui19/…

1
Retrieval, rerankers, and RAG tips and tricks | Data Brew | Episode 39 45:22

8 weeks fa45:22

45:22

In this episode, Andrew Drozdov, Research Scientist at Databricks, explores how Retrieval Augmented Generation (RAG) enhances AI models by integrating retrieval capabilities for improved response accuracy and relevance. Highlights include: - Addressing LLM limitations by injecting relevant external information. - Optimizing document chunking, embedding, and query generation for RAG. - Improving retrieval systems with embeddings and fine-tuning techniques. - Enhancing search results using re-rankers and retrieval diagnostics. - Applying RAG strategies in enterprise AI for domain-specific improvements.…

1
The Power of Synthetic Data | Data Brew | Episode 38 42:28

10 weeks fa42:28

42:28

In this episode, Yev Meyer, Chief Scientist at Gretel AI, explores how synthetic data transforms AI and ML by improving data access, quality, privacy, and model training. Highlights include: - Leveraging synthetic data to overcome AI data limitations. - Enhancing model training while mitigating ethical and privacy risks. - Exploring the intersection of computational neuroscience and AI workflows. - Addressing licensing and legal considerations in synthetic data usage. - Unlocking private datasets for broader and safer AI applications.…

1
Secret to Production AI: Tools & Infrastructure | Data Brew | Episode 37 37:14

12 weeks fa37:14

37:14

In this episode, Julia Neagu, CEO & co-founder of Quotient AI, explores the challenges of deploying Generative AI and LLMs, focusing on model evaluation, human-in-the-loop systems, and iterative development. Highlights include: - Merging reinforcement learning and unsupervised learning for real-time AI optimization. - Reducing bias in machine learning with fairness and ethical considerations. - Lessons from large-scale AI deployments on scalability and feedback loops. - Automating workflows with AI through successful business examples. - Best practices for managing AI pipelines, from data collection to validation.…

1
Mixture of Memory Experts (MoME) | Data Brew | Episode 36 41:24

14 weeks fa41:24

41:24

In this episode, Sharon Zhou, Co-Founder and CEO of Lamini AI, shares her expertise in the world of AI, focusing on fine-tuning models for improved performance and reliability. Highlights include: - The integration of determinism and probabilism for handling unstructured data and user queries effectively. - Proprietary techniques like memory tuning and robust evaluation frameworks to mitigate model inaccuracies and hallucinations. - Lessons learned from deploying AI applications, including insights from GitHub Copilot’s rollout. Connect with Sharon Zhou and Lamini: https://www.linkedin.com/in/zhousharon/ https://x.com/realsharonzhou https://www.lamini.ai/…

1
Mixed Attention & LLM Context | Data Brew | Episode 35 39:11

21 weeks fa39:11

39:11

In this episode, Shashank Rajput, Research Scientist at Mosaic and Databricks, explores innovative approaches in large language models (LLMs), with a focus on Retrieval Augmented Generation (RAG) and its impact on improving efficiency and reducing operational costs. Highlights include: - How RAG enhances LLM accuracy by incorporating relevant external documents. - The evolution of attention mechanisms, including mixed attention strategies. - Practical applications of Mamba architectures and their trade-offs with traditional transformers.…

1
Kumo AI & Relational Deep Learning | Data Brew | Episode 34 43:27

26 weeks fa43:27

43:27

In this episode, Jure Leskovec, Co-founder of Kumo AI and Professor of Computer Science at Stanford University, discusses Relational Deep Learning (RDL) and its role in automating feature engineering. Highlights include: - How RDL enhances predictive modeling. - Applications in fraud detection and recommendation systems. - The use of graph neural networks to simplify complex data structures.…

1
LLMs: Internals, Hallucinations, and Applications | Data Brew | Episode 33 38:50

2 years fa38:50

38:50

Our fifth season dives into large language models (LLMs), from understanding the internals to the risks of using them and everything in between. While we're at it, we'll be enjoying our morning brew. In this session, we interviewed Chengyin Eng (Senior Data Scientist, Databricks), Sam Raymond (Senior Data Scientist, Databricks), and Joseph Bradley (Lead Production Specialist - ML, Databricks) on the best practices around LLM use cases, prompt engineering, and how to adapt MLOps for LLMs (i.e., LLMOps).…

1
Demonstrate–Search–Predict Framework | Data Brew | Episode 32 33:14

2 years fa33:14

33:14

We will dive into LLMs for our fifth season, from understanding the internals to the risks of using them and everything in between. While we’re at it, we’ll be enjoying our morning brew. In this session, we interviewed Omar Khattab - Computer Science Ph.D. Student at Stanford, creator of DSP (Demonstrate–Search–Predict Framework), to discuss DSP, common applications, and the future of NLP.…

1
Generative AI Risks | Data Brew | Episode 31 34:38

2 years fa34:38

34:38

We will dive into LLMs for our fifth season, from understanding the internals to the risks of using them and everything in between. While we’re at it, we’ll be enjoying our morning brew. In this session, we interviewed Yaron Singer, CEO of Robust Intelligence, Professor of Computer Science at Harvard University, and guest of Data Brew Season 3 (our first repeat guest!). In this session, we discuss generative AI, the trends toward embracing LLMs, and how the surface area for vulnerabilities in generative AI is much bigger.…

1
John Snow Labs & SparkNLP | Data Brew | Episode 30 43:17

2 years fa43:17