Podcast
Machine Learning Made Simple
Hosted by Saugata Chatterjee · EN
🎙️ Machine Learning Made Simple – The Podcast That Unpacks AI Like Never Before!
👀 What’s behind the AI revolution?
Whether you're a tech leader, an ML engineer, or just fascinated by AI, we break down complex ML topics into easy, engaging discussions. No fluff—just real insights, real impact.
🔥 New episodes every week!
🚀 AI, ML, LLMs & Robotics—Simplified!
🎧 Listen Now on Spotify
📺 Prefer visuals? Watch on YouTube: https://www.youtube.com/watch?v=zvO70EtCDBE&list=PLHL9plgoN5KKlRRHvffkdon8ChZ
🌍 More AI insights?: https://www.youtube.com/@TheAIStack
12episodes
Episodes
Newest firstAll episodes
Episode 61: DeepSeek Models Explained - Part II
Feb 4, 2025Tap to summarizeWhat if AI could be 95% cheaper? Discover how DeepSeek's game-changing models are reshaping the AI landscape through breakthrough innovations. Journey through the evolution of AI optimization, from GPU efficiency to revolutionary attention mechanisms. Learn when to use (and when to avoid) these powerful new models, with practical insights for both individual users and businesses. Key highlights: How DeepSeek achieves dramatic cost reduction through technical innovation Real-world implications for consumers and enterprises Critical considerations around data privacy and model alignment Practical guidance on responsible implementation References: Dario Amodei — On DeepSeek and Export Controls Bite: How Deepseek R1 was trained [2501.17161] SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training [2405.04434] DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model [2408.15664] Auxiliary-Loss-Free Load Balancing Strategy for Mixture-of-Experts [2412.19437] DeepSeek-V3 Technical Report [2501.12948] DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
Transcribe →Episode 55: The Single Pixel That Tricks Every AI
Dec 11, 2024Tap to summarizeCould a few altered pixels make AI see a school bus as an ostrich? From data poisoning attacks that corrupt systems to groundbreaking defenses that keep AI trustworthy, explore the critical challenges shaping our AI future. Discover how today's security breakthroughs protect everything from spam filters to autonomous systems. Highlights: How tiny changes can fool powerful AI models The four levels of AI safety explained Cutting-edge defense strategies in action Real-world cases of AI manipulation and solutions References for main topic: Adversarial Machine Learning∗ Multiple classifier systems for robust classifier design in adversarial environments | Request PDF [1312.6199] Intriguing properties of neural networks [1412.6572] Explaining and Harnessing Adversarial Examples [2106.09380] Modeling Realistic Adversarial Attacks against Network Intrusion Detection Systems
Transcribe →