Check out the latest (and most visual) video on this topic! The Celestial Mechanics of Attention Mechanisms: https://www.youtube.com/watch?v=RFdb2rKAqFw

Attention mechanisms are crucial to the huge boom LLMs have recently had.
In this video you'll see a friendly pictorial explanation of how attention mechanisms work in Large Language Models.

This is the first of a series of three videos on Transformer models.
Video 1: The attention mechanism in high level (this one)
Video 2: The attention mechanism with math: https://www.youtube.com/watch?v=UPtG_38Oq8o
Video 3: Transformer models https://www.youtube.com/watch?v=qaWMOYf4ri8

Learn more in LLM University! https://llm.university

A video about autoencoders, a very powerful generative model. The video includes:
Intro: (0:25)
Dimensionality reduction (3:35)
Denoising autoencoders (10:50)
Variational autoencoders (18:15)
Training autoencoders (23:36)

Github repo: www.github.com/luisguiserrano/autoencoders

Recommended videos:
Generative adversarial networks: https://www.youtube.com/watch?v=8L11aMN5KY8
Restricted Boltzmann machines: https://www.youtube.com/watch?v=Fkw0_aAtwIw
Matrix factorization: https://www.youtube.com/watch?v=ZspR5PZemcs
Singular value decomposition: https://www.youtube.com/watch?v=DG7YTlGnCEo
Neural networks: https://www.youtube.com/watch?v=BR9h47Jtqyw
Convolutional neural networks: https://www.youtube.com/watch?v=2-Ol7ZB0MmU
Recurrent neural networks: https://www.youtube.com/watch?v=2-Ol7ZB0MmU
Logistic regression: https://www.youtube.com/watch?v=jbluHIgBmBo
Shannon entropy: https://www.youtube.com/watch?v=9r7FIXEAGvs

Book by Luis Serrano! Grokking Machine Learning. bit.ly/grokkingML
40% discount code: serranoyt

0:00 Introduction
0:13 Generative models
3:03 Variational autoencoders
3:45 Dataset of images
10:16 Denoising autoencoders
10:27 Linear methods
10:53 A friendly introduction to deep learning and neural networks
11:58 Mapping the real numbers to the interval (0,1)
12:23 Sigmoid function
12:41 Perceptron
15:02 Correct noise
18:20 Autoencoders as generators
20:16 Latent space
23:41 Training a neural network - loss function
25:18 Training an autoencoder
25:32 Training autoencoders
25:46 Reconstruction loss (Mean squared error)
26:31 Reconstruction loss (log-loss)
27:11 Training a variational auto encoder

Correction: At 30:05, the number in the middle of the red graph should be 0.4, not 0.3.

Read about this in more detail in my latest blog post: https://www.builder.io/blog/train-ai

#ai #developer #javascript #react

Full courses + unlimited support: https://www.skool.com/ai-autom....ation-society-plus/a
All my FREE resources: https://www.skool.com/ai-automation-society/about
Work with me: https://uppitai.com/

My Tools💻
14 day FREE n8n trial: https://n8n.partnerlinks.io/22crlu8afq5r
Code NATEHERK to Self-Host n8n for 10% off (annual plan): http://hostinger.com/nateherk
Voice to text: https://ref.wisprflow.ai/nateherk



In this video, I break down building an AI Agent so simply even a 10-year-old could do it! I’ll walk you through what an AI agent is and how to build a basic email agent in n8n that can automatically send emails for you.

No coding experience? No problem! I’ll guide you step-by-step, showing just how quick and easy you can get this set up. By the end of this video, you’ll have your very own email-sending AI agent up and running in no time.


Sponsorship Inquiries:
📧 sponsorships@nateherk.com

WATCH NEXT:
https://youtu.be/u2Tuu02r7QI

TIMESTAMPS
00:00 Components of an AI Agent
03:50 Step 1: Chat Input
04:18 Step 2: Adding the Brain
05:49 Step 3: Adding Memory
07:45 Step 4: Adding Send Email Tool
10:21 Step 5: Adding Instructions (System Message)
12:04 Testing the Email Agent
13:43 Reviewing the Agent Log
15:00 Step 6: Adding Contact Database Tool
16:57 Final Test
18:05 Final Thoughts

Gear I Used:
Camera: Razer Kiyo Pro
Microphone: HyperX SoloCast
Background Music: https://www.youtube.com/watch?v=Q7HjxOAU5Kc&t=0s

Try Notion for free → https://ntn.so/techwithtim

👉 Check out PyCharm, the only Python IDE you need. Built for web, data, and AI/ML professionals. Download now. Free forever, plus one month of Pro included: https://jb.gg/check_out_pycharm_ide

Today I'm going to show you how to build an AI agent in Python in less than ten minutes.

Want to make real money with coding? I share high-signal insights on careers, monetization, and leverage in my free newsletter. Join here and get my guide How to Make Money With Coding instantly: https://techwithtim.net/newsletter

🎞 Video Resources 🎞
UV Video: https://www.youtube.com/watch?v=6pttmsBSi8M
Code in this video: https://github.com/techwithtim..../PythonAIAgentin10Mi

⏳ Timestamps ⏳
00:00 | Install & Setup
01:23 | OpenAI API Key
03:26 | Imports
04:42 | Tools
06:39 | LLM & Agent
07:43 | Driver Code
09:45 | Testing

Hashtags
#Python #AIAgents #Notion

This is my 50 Claude Code tips from 6 months of daily use personally and at Meta as a Staff Software Engineer. I've been coding with Claude Code basically 12 hours a day really trying to understand what makes Claude Code tik. Here's everything I wish I knew when I started, from foundations to advanced parallel workflows.

⏱️ TIMESTAMPS
0:00 - Intro
1:04 - ACT 1: Foundations (Tips 1-25)
1:18 - Tip 1: Run from root directory
1:56 - Tip 2: Run /init immediately
2:54 - Tip 3: CLAUDE.md is hierarchical
3:27 - Tip 4: Keep CLAUDE.md concise
3:58 - Tip 5: Structure: What, Domain, Validation
5:36 - Keyboard Shortcuts
5:58 - Tip 6: Shift+Tab toggles modes
6:40 - Tip 7: Escape interrupts
7:43 - Tip 8: Double Escape clears input
7:59 - Tip 9: Double Escape on empty = rewind
8:29 - Tip 10: Screenshot and drag
8:44 - Tip 11: Add context to screenshots
9:09 - Essential Commands
9:41 - Tip 12: /clear resets context
10:13 - Tip 13: /context shows token usage
11:42 - Tip 14: Let auto-compaction work
12:23 - Tip 15: /model switches models
12:49 - Tip 16: /resume recovers sessions
13:21 - Tip 17: /mcp shows MCP status
14:19 - Tip 18: /help shows all commands
14:33 - Tip 19: Git is your safety net
15:24 - CLAUDE.md Deep Dive
15:52 - Tip 20: Add a Critical Rules section
17:08 - Tip 21: Ask Claude to update rules
17:46 - Tip 22: Use workflow triggers
18:27 - Tip 23: Commit CLAUDE.md to git
19:34 - Tip 24: dangerously-skip for throwaway envs
20:39 - Tip 25: Combine skip with allowlists
20:59 - ACT 2: Daily Workflow (Tips 26-32)
21:38 - Tip 26: Start features in Plan Mode
23:46 - Tip 27: Fresh context beats bloated
24:29 - Tip 28: Persist before ending sessions
25:03 - Tip 29: Lazy load context
26:09 - Tip 30: Give verification commands
27:32 - Tip 31: Consider Opus for complex work
28:18 - Tip 32: Read thinking blocks
29:01 - ACT 3: Power User (Tips 33-40)
29:34 - Tip 33: Four composability primitives
29:54 - Tip 34: Skills = recurring workflows
31:33 - Tip 35: Commands = quick shorthand
32:18 - Tip 36: Never create commands manually
33:02 - Tip 37: MCPs = external service docs
33:52 - Tip 38: Ask Claude to install MCPs
34:15 - Tip 39: Subagents = isolated context
37:10 - Tip 40: Avoid instruction overload
37:48 - ACT 4: Advanced (Tips 41-50)
38:02 - Tip 41: Run multiple instances
39:06 - Tip 42: iTerm split panes
40:33 - Tip 43: Enable notifications
41:10 - Tip 44: Git worktrees for isolation
41:40 - Tip 45: /chrome connects browser
43:17 - Tip 46: Powerful for debugging
43:28 - Hooks & Automation
43:41 - Tip 47: Hooks intercept actions
44:10 - Tip 48: Auto-format with PostToolUse
44:24 - Tip 49: Block dangerous commands
44:43 - Tip 50: Explore the plugin ecosystem
45:32 - Context is King (Outro)

📬 NEWSLETTER
Weekly deep dives on AI coding, developer productivity, and engineering career growth. https://getpushtoprod.substack.com

📺 MORE RELATED VIDEOS

Claude Code Workflows That Will 10x Your Productivity https://youtu.be/yZvDo_n12ns?si=ChHm_yo2d8SONVZ6

Vibe Coding is Making Engineers Worse (Do This Instead)
https://youtu.be/LnNlwEMlb1A?si=wWmoqmxd0K4F0g5L

📲 CONNECT WITH ME
► LinkedIn → / jonnykvids
► Instagram → / @jonnykvids
► Threads → https://www.threads.net/@jonnykvids

👍 Like, Subscribe & Hit the Bell for more software engineering insights!

#claudecode #aicoding #programming

MIT 15.773 Hands-On Deep Learning Spring 2024
Instructor: Rama Ramakrishnan
View the complete course: https://ocw.mit.edu/courses/15....-773-hands-on-deep-l
YouTube Playlist: https://www.youtube.com/playli....st?list=PLUl4u3cNGP6

Covers transfer learning, convolutional neural network (CNN) models, pooling layers, and application examples, including a handbags-shoes classifier.

License: Creative Commons BY-NC-SAMore information at https://ocw.mit.edu/termsMore courses at https://ocw.mit.eduSupport OCW at http://ow.ly/a1If50zVRlQ

We encourage constructive comments and discussion on OCW’s YouTube and other social media channels. Personal attacks, hate speech, trolling, and inappropriate comments are not allowed and may be removed. More details at https://ocw.mit.edu/comments.

(March 29, 2010) Stanford professor Robert Sapolsky gave the opening lecture of the course entitled Human Behavioral Biology and explains the basic premise of the course and how he aims to avoid categorical thinking.

Stanford University
http://www.stanford.edu

Stanford Department of Biology
http://biology.stanford.edu/

Stanford University Channel on YouTube
http://www.youtube.com/stanford

Deep learning is essential to developing cutting-edge AI, including image recognition, sound and voice recognition, and complex generative learning models - to name a few. Using Python within Anaconda, the process of building these models is easier with updated packages, security concerns mitigated, clean and clear notebooks, and multiple platforms installed at once.