Challenges and Solutions in Managing Code Security for ML Developers - ML 175

Challenges and Solutions in Managing Code Security for ML Developers - ML 175

Today, join Michael and Ben as they delve into crucial topics surrounding code security and the safe execution of machine learning models. This episode focuses on preventing accidental key leaks in notebooks, creating secure environments for code execution, and the pros and cons of various isolation methods like VMs, containers, and micro VMs.
They explore the challenges of evaluating and executing generated code, highlighting the risks of running arbitrary Python code and the importance of secure evaluation processes. Ben shares his experiences and best practices, emphasizing human evaluation and secure virtual environments to mitigate risks.
The episode also includes an in-depth discussion on developing new projects with a focus on proper engineering procedures, and the sophisticated efforts behind Databricks' Genie service and MLflow's RunLLM. Finally, Ben and Michael explore the potential of fine-tuning machine learning models, creating high-quality datasets, and the complexities of managing code execution with AI.
Tune in for all this and more as we navigate the secure pathways to responsible and effective machine learning development.


Socials


Become a supporter of this podcast: https://www.spreaker.com/podcast/adventures-in-machine-learning--6102041/support.

Jaksot(209)

How To Do Research Spikes - ML 093

How To Do Research Spikes - ML 093

Have you ever wondered how to efficiently learn topics? In this episode, we discuss how to conduct a research spike within an ML team setting. SponsorsChuck's Resume TemplateDeveloper Book Club starting with Clean Architecture by Robert C. MartinBecome a Top 1% Dev with a Top End Devs MembershipAdvertising Inquiries: https://redcircle.com/brandsPrivacy & Opt-Out: https://redcircle.com/privacyBecome a supporter of this podcast: https://www.spreaker.com/podcast/adventures-in-machine-learning--6102041/support.

10 Marras 202246min

How to Simplify Data Science with DagsHub Founders - ML 092

How to Simplify Data Science with DagsHub Founders - ML 092

Have you ever wondered why data science is hard? Well, in this episode we cover some common data science challenges and how the founders of DagsHub are looking to solve them.  SponsorsTop End DevsCoaching | Top End DevsLinksDean PlebanAdvertising Inquiries: https://redcircle.com/brandsPrivacy & Opt-Out: https://redcircle.com/privacyBecome a supporter of this podcast: https://www.spreaker.com/podcast/adventures-in-machine-learning--6102041/support.

27 Loka 202248min

How to Test ML Code - ML 091

How to Test ML Code - ML 091

In this show, we cover some practical tips for writing reliable ML code. Here are some of the questions we look to answer...What are tests and why should you use them?What's the difference between unit tests and integration tests?What should you test?How should you write tests in python? (the answer is to use pytest)SponsorsTop End DevsCoaching | Top End DevsEnov8, who provides test data managementAdvertising Inquiries: https://redcircle.com/brandsPrivacy & Opt-Out: https://redcircle.com/privacyBecome a supporter of this podcast: https://www.spreaker.com/podcast/adventures-in-machine-learning--6102041/support.

20 Loka 202244min

AGI, Neuron Simulators, and More with Charles Simon - ML 090

AGI, Neuron Simulators, and More with Charles Simon - ML 090

Charles Simon, BSEE, MSCs is a nationally recognized entrepreneur and software developer who has many years of computer experience in industry including pioneering work in artificial intelligence (AI).  Mr. Simon's technical experience includes the creation of two unique AI systems along with software for successful neurological test equipment combining AI development with biomedical nerve signal testing that gives him the singular insight.  Today on the show, Charles, Michael, and Ben explore the riveting future of AGI and other illuminating technology concepts.  This is an exciting episode you won’t want to miss! In this episode…Charles Simon’s extensive backgroundClassical algorithms vs manual designKnowledge and power generated in our brainsAI and ML concepts and learning patternsGraph based approaches and deep learning“Terminator” and AGIFuture AI and open source simulatorLeveraging technology to solve problems SponsorsTop End DevsCoaching | Top End DevsLinksThe TeamLinkedIn: Charles SimonAdvertising Inquiries: https://redcircle.com/brandsPrivacy & Opt-Out: https://redcircle.com/privacyBecome a supporter of this podcast: https://www.spreaker.com/podcast/adventures-in-machine-learning--6102041/support.

6 Loka 20221h 4min

Complex ML Models with Data Scientist Fernando Lopez - ML 089

Complex ML Models with Data Scientist Fernando Lopez - ML 089

Fernando Lopez joins the show today to share his ML insights with a video interview recruiting platform for candidate hiring.  Michael and Ben also deep dive into various related ML models and AI topics. In this episode…Core software engineering skillsPractice data algorithms and structures Working towards production-grade MLData engineering and data structuresUsing state-of-the-art models Applying labels to dataThe AI revolution Eliminating bias and unweighted data setUnconscious and conscious exercisesComplex models with structureSponsorsTop End DevsCoaching | Top End DevsLinksHow to Package and Distribute Machine Learning Models with MLFlow - KDnuggetsTwitter: @ferneutronnAdvertising Inquiries: https://redcircle.com/brandsPrivacy & Opt-Out: https://redcircle.com/privacyBecome a supporter of this podcast: https://www.spreaker.com/podcast/adventures-in-machine-learning--6102041/support.

29 Syys 202257min

Distributed Time Series in Machine Learning - ML 088

Distributed Time Series in Machine Learning - ML 088

Today the panel discusses high level distributed time series models, using a hot dog stand company as the case study to anchor the understanding with these models. In this episode…Understanding use caseML flow models and eventsKPI forecastsMetadata outputsPrediction intervals for hotdog dataAutomated time series forecastsLibraries required for optimizationPractical tips managing the data andSetting up the data for consumptionManaging black swan eventsSponsorsTop End DevsCoaching | Top End DevsAdvertising Inquiries: https://redcircle.com/brandsPrivacy & Opt-Out: https://redcircle.com/privacyBecome a supporter of this podcast: https://www.spreaker.com/podcast/adventures-in-machine-learning--6102041/support.

22 Syys 202247min

Time Series Models in Machine Learning - ML 087

Time Series Models in Machine Learning - ML 087

Today on the show, the panel discusses time series models, practical tips and tricks, and shares stories and examples of various models and the processes for optimal application in your ML workflows. In this episode…Ben’s time series model for sales forecastingThe flat line modelExamples using time series modelsUnderstanding your dataLag functions and moving averages Signal processing in modelsManually adding change pointsDeep learning in time series models SponsorsTop End DevsCoaching | Top End DevsAdvertising Inquiries: https://redcircle.com/brandsPrivacy & Opt-Out: https://redcircle.com/privacyBecome a supporter of this podcast: https://www.spreaker.com/podcast/adventures-in-machine-learning--6102041/support.

15 Syys 202253min

Optical Character Recognition (OCR) and Machine Learning with Ahmad Anis - ML 086

Optical Character Recognition (OCR) and Machine Learning with Ahmad Anis - ML 086

Optical character recognition, or OCR for short, is used to describe algorithms and techniques (both electronic and mechanical) to convert images of text to machine-encoded text.  Today on the show, Ahmad Anis shares how he applies Machine Learning to OCR for small hardware applications, for example, blurring a face in a video in real time or on a stream to safeguard privacy using AI.  The panel also discusses various strategies related to learning and soft skills needed for success within the industry. In this episode…Optical character recognition (OCR) definedMultiprocessing vs. multithreading I/O bound tasks vs. CPU tasksHow to handle a retry in PythonStrategies for employing on small hardware Template matching and preprocessing Gray scaling integrationsHow to learn and get started within the industryReducing the scope and industry soft skills SponsorsTop End DevsCoaching | Top End DevsLinksLinkedIn: Ahmad AnisTwitter: @AhmadMustafaAn1Advertising Inquiries: https://redcircle.com/brandsPrivacy & Opt-Out: https://redcircle.com/privacyBecome a supporter of this podcast: https://www.spreaker.com/podcast/adventures-in-machine-learning--6102041/support.

8 Syys 202253min

Suosittua kategoriassa Liike-elämä ja talous

puheenaihe
psykopodiaa-podcast
mimmit-sijoittaa
sijotuskasti
rss-rahapodi
pomojen-suusta
ostan-asuntoja-podcast
herrasmieshakkerit
rss-neuvottelija-sami-miettinen
hyva-paha-johtaminen
raharesepti
rss-tyoelaman-timantteja
inderespodi
oppimisen-psykologia
juristipodi
sijoituspodi
rss-paikoillenne-valmiit-laakikseen
rss-startup-ministerio
rss-myynti-ei-ole-kirosana
rss-vastuullisuus-tyoelamassa