I create content about deep learning | The DevRel and Deep Learning Dude

Hacking on LLMs, curating multimodal datasets, and writing a book about RAG.

Harpreet Sahota 🥑

i've literally been waiting for years to have an OPEN SOURCE model like qwen3-vl-embedding

i tested its multimodal retrieval capabilities on a corpus of 412 short video clips and the results literally blew my mind

here are the queries i tested:

1. a cartoon guy drinks merlot wine

i like this query because we see how it can retrieve based on semantics (a cartoon), text (the label merlot), and temporal action in the video (the cartoon guy drinks the wine mid-way through the video)

2. garfield runs out of the door

semantics are awesome here, the model knows i'm talking about the cartoon character...

3. a woman in a blue dress sleeping on a red bench

the skeptic in you might think that it's retrieving just based on the red color block in the 2/3 of the video...but notice the specific part of the query "a woman in a blue dress..." and this is only shown in 3s out of the full 10s

this is such a huge release 

and it's gonna open up SO much more for multimodal video retrieval this year

on my wishlist is natural language search of pcd datasets, who gonna ship that?

you can hack around with the model using the resources below

check out the docs: here: https://lnkd.in/gh7yfBNP

and the quickstart nbhere:  https://lnkd.in/gbinsx7p

🤖 Hacker-in-Residence @ Voxel51| 👨🏽‍💻 AI/ML Engineer | 👷🏽‍♀️ Technical Developer Advocate | Learn. Do. Write. Teach. Repeat.

for those who missed it, or were there in-person and know the trouble i was facing 😆, my ODSC webinar is now live on youtube!

in this session i discuss visual ai techniques for automotive damage detection. 

i used the cardd dataset, which is a public dataset built specifically for vehicle damage analysis and demonstrated how fiftyone helps you explore, visualize, and build models to detect dents, scratches, cracks, glass shatter, tire flats, and broken lamps.

i feel like its a super practical workshop with some insightful workflows for visual AI in automotive settings, but as the creator i might be biased.

only one way to find out for yourself, watch the webinar!

https://lnkd.in/ewfz5vZD

Open video: Mastering Visual AI with Vision-Language Models & Advanced Evaluation Techniques by Harpreet Sahota on youtube.com

Mastering Visual AI with Vision-Language Models & Advanced Evaluation Techniques by Harpreet Sahota

sometimes i look back at the shit i get done and i genuinely impress myself

how teams really build Visual AI in the wild? what's the he messy reality?  

i don't know...and maybe its because nobody’s asking practitioners and compiling their answers so we can find out the landscape actually looks like. 

so, we at Voxel51 are kickin off the...

wait for it...

 State of Visual AI survey...vey...vey

for those out ther building visual AI systems i want your hot takes

what’s the hardest part about making visual ai a reality? 

let us know in this survey

it'll take you 30 minutes and is a much better use of time than baby sitting your runs and staring at your loss curves

i can't offer much beyond my heartiest thanks, but you will get early access to the full report with benchmarks, common pain points, and where you stand within the landscape. 

here's a link: https://lnkd.in/gnsADACy

MedGemma 1.5 supports detection, but for best results, you'll need to fine-tune. 

there's a kaggle competition using the model, i created a starter notebook to give you a jump start on how to fine-tune it for detection

checkout the starter notebook and additonal resources 👇🏼

cc Omar Sanseviero Megan Risdal Logan Kilpatrick

in the asu area and wanna get started with open source contributions? then don't miss this hack

On March 21, 2026, we’re hosting Agents World: Visual AI Hackathon @Arizona State University, together with Pavan Turaga 🚀 

This is a hands-on day: meet people, build with AI, eat pizza, and leave with something you created after a short workshop and a full day of hacking. 
You’ll work with the FiftyOne ecosystem and real models used in practice, like Qwen, Gemini Vision, Sharp, and more. 

If you’re an ASU student who wants to build, learn by doing, and work with real Visual AI tools, this is for you.

Registration is open:
https://lnkd.in/gBCHW5Fg

Hope to see you at ASU. I’ll be there with the amazing Voxel51 team:  Sid Mehta, Ritchie Martori, Jimmy Guerrero ! 🙌

looking forward to the next meetup in boston!

Join our in-person meetup at the Microsoft Research Lab at the Massachusetts Institute of Technology in Boston, Massachusetts on Feb 18 to hear talks from experts on cutting-edge topics across AI, ML, and computer vision. Register here: https://lnkd.in/gi4kpSMB

Talks will include:

• SNAP: Towards Segmenting Anything in Any Point Cloud - Hanhui Wang at Northeastern University

• Culturally Adaptive AI - Anku R. at Massachusetts Institute of Technology

• Data Foundations for Vision-Language-Action Models - Harpreet Sahota 🥑 at Voxel51

• Better Together: Leveraging Unpaired Multimodal Data for Stronger Unimodal Models - Sharut G. at Massachusetts Institute of Technology

• Neural Radiance Fields for Image Verification - Sage Simhon at Pasteur Labs & ISI

#computervision #ai #artificialintelligence #machinevision #machinelearning #datascience

Syed Abdul Sami Rizvi, Matthew Ebisu and 118 other attendees

View event: Feb 18 - Boston AI, ML and Computer Vision Meetup

Feb 18 - Boston AI, ML and Computer Vision Meetup

Inspired by the amazing Hugging Face’s 2025 AI Timeline, we created one for the Fiftyone community. The FiftyOne Community Development Timeline highlights more than 131 contributions from 2025, including datasets, models, plugins, and integrations.

You can filter by type or modality and jump straight to each integration.
https://lnkd.in/ev2kpCGN

Big thanks to the entire Voxel51 community for building all of this together.
Harpreet Sahota 🥑, Daniel Gural, Paula Ramos, PhD, Jimmy Guerrero, Derek Van de Streek, Nicholas Lotz 🚀

Gonna be a great series of talks, lots of technical depth!

Chief Community Officer @ Voxel51 | Startup Advisor

Join us on Feb 18 for the Boston AI, ML and Computer Vision Meetup! Pre-registration is mandatory to clear building security - https://lnkd.in/gHtBuH49

Talks will include:

* SNAP: Towards Segmenting Anything in Any Point Cloud - Hanhui Wang at Northeastern University

* Culturally Adaptive AI - Anku R. at MIT

* Data Foundations for Vision-Language-Action Models - Harpreet Sahota 🥑 at Voxel51

* Better Together: Leveraging Unpaired Multimodal Data for Stronger Unimodal Models - Sharut G. at MIT

* Neural Radiance Fields for Image Verification - Sage Simhon at Pasteur Labs & ISI

***********

Want to build better computer vision models? FiftyOne is an open source toolkit from Voxel51 (our Meetup sponsor) that helps you curate datasets, evaluate model performance, visualize embeddings, catch annotation errors, and eliminate duplicate images—all in one place.

“pip install fiftyone” is all it takes to get started - https://docs.voxel51.com/

#computervision #ai #artificialintelligence #machinevision
#machinelearning #datascience #physicalai

81k | Director, Data & Analytics/ AI @ Gartner

Summary

Making state-of-the-art Artificial Intelligence concepts accessible and profitable to professionals from any background for over 35 years!

Highlights
-  Veteran innovator with 3 decades of experience leading state-of-the-art AI and Analytics ventures
-  98% of students surveyed would recommend me to peers
-  Generative AI/ Agentic AI expert-  ChatGPT, Claude, Copilot, Perplexity, Lovable, n8n, more
-  Experienced AI instructor for Cisco, LinkedIn Learning, University of Pennsylvania, & Simplilearn
-  Senior AI Curriculum Advisor for Graduate School of Education at Ivy League university UPenn
-  Winner, International Society of Data Scientists Outstanding Voice Award
-  Social media leader with over 107k LinkedIn followers


Selected Clients
 
-  3M
-  Audi
-  Biogen 
-  Booz Allen Hamilton
-  Bristol-Myers Squibb
-  Cisco
-  Citicorp
-  Franklin Templeton
-  Gartner/ Evanta
-  Harvard Innovation Labs’ Experfy
-  IBM
-  International Olympic Committee
-  Los Angeles Times
-  Mercedes
-  Morgan Stanley
-  Royal Bank of Canada
-  St. Jude’s Children’s Hospital
-  Wells Fargo
-  US Homeland Security
-  US Veterans Administration 
-  Yale University

Partial Skills Inventory
 
-  AIOps
-  Accountable AI/ Ethics
-  Anomaly Detection
-  Anthropic/ Claude
-  Artificial Intelligence
-  AWS
-  Brokerage Firms
-  Client Management
-  Consulting
-  Compelling Presentations
-  Compliance Regs and Frameworks
-  Curriculum Development
-  Dashboards
-  Data Storytelling
-  Data Visualization
-  Education
-  Explainable AI
-  Feature Engineering
-  Financial Services
-  Fraud Detection
-  Gap Analysis
-  Generative AI
-  GitHub Models
-  Google Cloud
-  Google Gemini
-  Insurance
-  KPI's and Metrics
-  Lovable AI
-  Machine Learning
-  Microsoft Azure
-  MLOps
-  Model Ensembles
-  Nano Banana
-  OpenAI/ ChatGPT
-  Orange Data Mining
-  Perplexity
-  Postgres SQL
-  Professional Development
-  Research
-  Retail
-  Retention and Attrition
-  SPSS
-  SQL Server
-  Underwriting

T. Scott Clendaniel

🔬 #ArtificialIntelligence 𝗛𝗶𝗿𝗶𝗻𝗴- 𝗝𝘂𝘀𝘁 𝗪𝗵𝗮𝘁 𝗔𝗥𝗘 𝗘𝗺𝗽𝗹𝗼𝘆𝗲𝗿𝘀 𝗟𝗼𝗼𝗸𝗶𝗻𝗴 𝗙𝗼𝗿?

The Terrible Facts:
- Artificial Intelligence needs a lot more experts.
- Tons of qualified professionals aren't getting hired.
- The expectations of hiring managers are just out of control.

If you're a hiring manager, please STOP looking for an entire department in just one employee.  It simply doesn't work that way.  You need a team.

Personally, I find the job search to be truly dreadful. It is exhausting, soul-crushing, depressing, dispiriting- actually, I will run out time before I run of negative emotions on this topic!  

But I hold out hope that one day everyone else will figure this out!

Please follow me for more analysis! 

- T. Scott Clendaniel

#AI Training for Executives | 108K LinkedIn Followers

It’s been a while since I started my role at Nautilus-AI.com as a Chief Learning Officer, but I wanted to share this update with everyone.

🔬 #ArtificialIntelligence: 𝗪𝗵𝗲𝗿𝗲 𝗗𝗼 𝗬𝗢𝗨 "𝗔𝗜"?

Our friends at GiGadgets researched something extraordinarily fun!

AI isn't the only place where innovation occurs.  Sometimes, the very desks we use to work with GenAI, Machine Learning, or any of the rest of AI occurs can show us remarkable creativity.

Take a look and smile!

- T. Scott Clendaniel

🔬 True Wisdom via Michael Tchuindjang!

Cybersecurity Thought Leader | Bridging Academia & Industry | Mentor for Startups & Aspiring Cyber Pros | Board Member Driving Cyber Impact | Associate Lecturer in Cybersecurity

Boardroom AI Strategy Meeting (2026 Edition) 



CEO: Who are we?
Boardroom: CEOs

CEO: What do we want?
Boardroom: AI!

CEO: AI to do what exactly?
Boardroom: We don’t know

CEO: When do we want it?
Boardroom: RIGHT NOW

If you’ve ever sat in a boardroom lately, this probably feels uncomfortably familiar.

AI has become the new magic word:

Replace “digital transformation”

Upgrade from “blockchain”

Stronger than “cloud-first”

Don’t get me wrong, AI is here to stay.

But AI without a clear problem, data readiness, risk assessment, or ethics is just… expensive enthusiasm.

Real innovation starts when we ask better questions:

What problem are we solving?
What risks are we introducing?
Who is accountable when AI fails?
Are humans still in the loop?

Otherwise, we’re not building AI strategies, we’re just speed-running confusion with a GPU 😄

Credits to @Cyber Writes ✍.

#ai #cybersecurity #security #leadership #aihype #responsibleai #jobs #hiringandpromotion #hiring #techhumor #humor #memes #klex

🎉 𝗚𝗲𝗻𝗔𝗜 𝗘𝗱𝘂𝗰𝗮𝘁𝗶𝗼𝗻 𝗪𝗶𝘁𝗵 𝗧𝗵𝗲 𝗣𝗲𝗿𝗶𝗼𝗱𝗶𝗰 𝗧𝗮𝗯𝗹𝗲! 

Here is the magic of video!

Generative AI can build entire new worlds.  This is one I absolutely love.  Mini planets made from elements in the period table:


𝗘𝗹𝗲𝗺𝗲𝗻𝘁𝘀

▶ 1.  Copper
▶ 2.  Mercury
▶ 3.  Calcium

▶ 4.  Magnesium
▶ 5.  Palladium
▶ 6.  Uranium

▶ 7.  Arsen
▶ 8.  Lead
▶ 9.  Chlorine

Happy Chemistry

Please SAVE and SHARE!  You can follow me: T. Scott Clendaniel

🔬 𝗧𝗲𝗮𝗰𝗵𝗶𝗻𝗴 #AI: 𝗦𝘁𝗲𝗮𝗹𝗶𝗻𝗴 𝗮 𝗩𝗶𝗱𝗲𝗼 𝗘𝘅𝗮𝗺𝗽𝗹𝗲 𝗳𝗿𝗼𝗺 𝗚𝗲𝗼𝗺𝗲𝘁𝗿𝘆!

Picture this: you’re holding a cube. It’s got 8 corners, 12 edges, and 6 faces. 

Add the corners and faces, subtract the edges, and you always get 2. Every time. That’s Euler’s Polyhedron Formula—V - E + F = 2. It works for a cube, a pyramid, even a soccer ball.

So why does that matter? Because it’s a reminder that under all complexity, there’s structure. Euler didn’t just find a number—he found a pattern that connects everything.

That’s how I think about explaining AI. The goal isn’t to drown people in details; it’s to show the structure beneath the surface. When you connect data (edges), decisions (vertices), and outcomes (faces) just right, people get it.

The best teachers—whether they’re explaining geometry or generative AI—make the complex feel simple and the simple feel profound. That’s how real understanding sticks.

Happy Learning,

T. Scott Clendaniel

🔬 #ArtificialIntelligence 𝗶𝗻 𝗗𝗲𝘀𝗶𝗴𝗻: 𝗣𝗿𝗼𝘀𝘁𝗵𝗲𝘁𝗶𝗰 𝗟𝗶𝗺𝗯𝘀!

SoftFoot Pro is a cutting-edge, motorless prosthetic foot developed by Italian researchers, mimicking human foot anatomy with flexible chains and titanium to adapt passively to terrain, offering better stability, natural movement (like bending), and improved energy efficiency for amputees, and also serving as a robotic component. 


---
𝗞𝗲𝘆 𝗙𝗲𝗮𝘁𝘂𝗿𝗲𝘀 & 𝗕𝗲𝗻𝗲𝗳𝗶𝘁𝘀
---

▶▶ 𝗛𝘂𝗺𝗮𝗻-𝗜𝗻𝘀𝗽𝗶𝗿𝗲𝗱 𝗗𝗲𝘀𝗶𝗴𝗻
Emulates the shape and structures of the human foot, including the plantar fascia, using flexible components.

▶▶ 𝗣𝗮𝘀𝘀𝗶𝘃𝗲 𝗔𝗱𝗮𝗽𝘁𝗮𝘁𝗶𝗼𝗻
Its flexible sole and chain system allow it to deform and widen its contact area, naturally adapting to rough or slippery surfaces without motors.

▶▶ 𝗜𝗺𝗽𝗿𝗼𝘃𝗲𝗱 𝗠𝗼𝗯𝗶𝗹𝗶𝘁𝘆
Enhances stability, allows for natural actions like bending down, and makes navigating stairs easier for users.

▶▶ 𝗟𝗶𝗴𝗵𝘁𝘄𝗲𝗶𝗴𝗵𝘁 & 𝗦𝘁𝗿𝗼𝗻𝗴
Weighs about 450g and supports up to 100kg, using titanium/aluminum and high-strength plastic chains.

Have a great week!

Follow me for more tips: T. Scott Clendaniel

🔬  #GenAI- 𝗜𝗻𝘁𝗿𝗼𝗱𝘂𝗰𝘁𝗶𝗼𝗻 𝘁𝗼 𝗖𝗼𝗻𝘃𝗼𝗹𝘂𝘁𝗶𝗼𝗻𝗮𝗹 𝗡𝗲𝘂𝗿𝗮𝗹 𝗡𝗲𝘁𝘄𝗼𝗿𝗸𝘀!

CNN's are the basis for many tools, including most of the computer vision, image, and video generation for Generative AI.  Here's how to teach it to your team.


𝗧𝗵𝗲 𝗕𝗮𝘀𝗶𝗰𝘀

A convolutional neural network (CNN) is a regularized type of feed-forward neural network that learns features by itself via filter (or kernel) optimization. This type of deep learning network has been applied to process and make predictions from many different types of data including text, images and audio.

Convolution-based networks are the de-facto standard in deep learning-based approaches to computer vision and image processing, and have only recently have been replaced -- in some cases -- by newer deep learning architectures such as the transformer. Vanishing gradients and exploding gradients, seen during backpropagation in earlier neural networks, are prevented by using regularized weights over fewer connections.

For example, for each neuron in the fully-connected layer, 10,000 weights would be required for processing an image sized 100 × 100 pixels. However, applying cascaded convolution (or cross-correlation) kernels, only 25 neurons are required to process 5x5-sized tiles. Higher-layer features are extracted from wider context windows, compared to lower-layer features.


𝗦𝗼𝗺𝗲 𝗔𝗽𝗽𝗹𝗶𝗰𝗮𝘁𝗶𝗼𝗻𝘀 𝗼𝗳 𝗖𝗡𝗡'𝘀

▶▶   image and video recognition
▶▶   recommender systems
▶▶   image classification
▶▶   image segmentation

▶▶   medical image analysis
▶▶   natural language processing
▶▶   brain–computer interfaces
▶▶   financial time series

CNNs are also known as shift invariant or space invariant artificial neural networks, based on the shared-weight architecture of the convolution kernels or filters that slide along input features and provide translation-equivariant responses known as feature maps.  Counter-intuitively, most convolutional neural networks are not invariant to translation, due to the downsampling operation they apply to the input.

Via Wikipedia ==> https://bit.ly/4126GDT

Happy Learning,

T. Scott Clendaniel

🔬 "𝗜𝗳 𝗬𝗼𝘂𝗿 𝗔𝗜 𝗧𝗿𝗮𝗶𝗻𝗶𝗻𝗴 𝗜𝘀 𝗕𝗼𝗿𝗶𝗻𝗴, 𝗜𝘁'𝘀 𝗕𝗲𝗶𝗻𝗴 𝗧𝗮𝘂𝗴𝗵𝘁 𝗕𝘆 𝗧𝗵𝗲 𝗪𝗿𝗼𝗻𝗴 𝗣𝗲𝗿𝘀𝗼𝗻!"

Okay, so Richard Feynman wrote the original quote about Science in general, not about Artificial Intelligence specifically.  So I confess.  I took a wee bit of dramatic license!

But UNILAD captured this fantastic video of Tatiana Erukhimova in here element teaching Physics.

And quite frankly, AI has a lot more possibilities for interactive content!

So no excuses!

And if you need help, reach out to me directly!  🤗 

- T. Scott Clendaniel




🎥 credits UNILAD/ Texas A&M University

🔬 #AI #Education:
Introducing 𝗥𝗲𝗶𝗻𝗳𝗼𝗿𝗰𝗲𝗺𝗲𝗻𝘁 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 demo- with 𝗣𝗨𝗣𝗣𝗜𝗘𝗦! 🐶🐶🐶

In the world of AI, Reinforcement Learning is truly a star, and the basis of things like self-driving cars/ autonomous vehicles.

It contains a few elements:

▶  Problem to be solved
▶  An agent, who is observed trying to solve the problem
▶  Reward/ penalty functions
▶  Scoring system

Just like these adorable puppies, who serve as our agents, trying to learn how to reach the treats, our agents try to figure out the problem.  Each puppy's success or failure is recorded, and the reinforcement learning system eventually solves the puzzle!

Enjoy!

T. Scott Clendaniel

🔬 𝗠𝗮𝗸𝗲 𝗬𝗼𝘂𝗿 𝗔𝗿𝘁𝗶𝗳𝗶𝗰𝗶𝗮𝗹 𝗜𝗻𝘁𝗲𝗹𝗹𝗶𝗴𝗲𝗻𝗰𝗲 𝗧𝗿𝗮𝗶𝗻𝗶𝗻𝗴 𝗖𝗼𝗺𝗲 𝗔𝗹𝗶𝘃𝗲!

The art of surprise will help your learners stay intrigued as you go through your training!


𝗖𝗮𝗻 𝗬𝗢𝗨 𝗳𝗶𝗴𝘂𝗿𝗲 𝗼𝘂𝘁 𝘁𝗵𝗲 𝘀𝘂𝗿𝗽𝗿𝗶𝘀𝗲 𝗕𝗘𝗙𝗢𝗥𝗘 𝘆𝗼𝘂 𝗰𝗹𝗶𝗰𝗸 𝗽𝗹𝗮𝘆?  Tell me in the comments below!

Please make sure to #SAVE and #REPOST so your followers can take advantage of the advice!

- T. Scott Clendaniel

taplio

The Battle

Harpreet Sahota 🥑

T. Scott Clendaniel

Followers

Posts

Engagements

Likes

Performance ScoreHarpreet Sahota 🥑's LinkedIn Performance

Performance ScoreT. Scott Clendaniel's LinkedIn Performance

Ready to grow your LinkedIn presence?

taplio

The Battle

Harpreet Sahota 🥑

T. Scott Clendaniel

Followers

Posts

Engagements

Likes

Performance Score.css-goub6s{font-size:var(--chakra-fontSizes-md);font-weight:500;color:var(--chakra-colors-gray-600);display:block;margin-top:var(--chakra-space-1);}Harpreet Sahota 🥑's LinkedIn Performance

Performance ScoreT. Scott Clendaniel's LinkedIn Performance

Ready to grow your LinkedIn presence?

Performance ScoreHarpreet Sahota 🥑's LinkedIn Performance