Videos de machine learning
Videos etiquetados con "machine learning"
machine learning 28 videos
04 How Large Language Models (LLMs) Works? | All about LLMs | What are Tokens & Context Length?
Generative AI | LLM | GenAI | NN | Large Language Models ⏰ Scheduled to be Public from Members Only on 01st Jun 2026 16:00 HRS IST ⏰ ===== In this video, you will learn ===== What is Large Language Model? What is LLM? How LLMs work? Next Token Prediction in LLM, What are Tokens and Context Length? Importance on Tokens in LLM, Different Sampling Controls, LLM Personas and Prompts, Probability Distribution for LLMs ===== Chapters ===== 00:00 - Introduction 00:27 - What are Large Language Models or LLMs? 03:44 - How Large is Large in LLMs? 05:44 - Transformers 08:07 - What are Tokens and their Importance in LLM? 08:18 - What is Vocabulary in LLM? 14:27 - Probability Distribution for Tokens 19:01 - Sampling Controls - Temperature, Top-p 25:51 - Auto-Regressive Generation Loop 28:53 - How LLMs preserves meaning? 30:58 - How LLMs are Trained? 33:15 - What is Fine Tuning? 34:28 - LLM Personas/Roles and Prompts 36:55 - What is Context Length? 39:01 - Model Knowledge Cutoff and Hallucination 41:23 - Open and Closed LLM Models 42:36 - Reasoning Models 43:24 - Multimodal Models ===== Links ===== Google's "Attention is all You Need" Paper - https://arxiv.org/pdf/1706.03762 Groq Cloud - https://console.groq.com/home GPT Tokenizer - https://platform.openai.com/tokenizer ===== Other Playlists ===== Checkout all other playlists on Data Engineering 👇🏻 https://www.youtube.com/@easewithdata/playlists ===== GitHub Repo ===== https://github.com/subhamkharwal ===== Connect with ME ===== LinkedIn - https://www.linkedin.com/in/subhamkharwal Medium - https://subhamkharwal.medium.com ===== Hashtags ==== #genai #dataengineering #python #agenticai #aiagents #aiagent #nn #neuralnetworks
Did you get laid off this Summer? YOU ARE NOT ALONE
Some changes happen slowly. Others happen all at once. Across the world, thousands of people are being forced to rethink their careers, their skills, and their future. The reasons might surprise you. This video explores a shift that is affecting workers, students, and entire industries around the world. The numbers are surprising, the consequences are real, and the conversation is long overdue. In this video, we break down why thousands of workers are losing their jobs, what's driving the changes inside major technology companies, and what it means for the future workforce. 👇 Let me know in the comments: Do you think the next generation will have better opportunities than today's workforce? ⏱️ Chapters 00:00 The Shocking Number 00:45 Tech Layoffs By The Numbers 01:45 Why Companies Are Really Cutting Jobs 02:45 Who Is Getting Hit The Hardest? 03:30 The AI Hiring Paradox 📈 Topics Covered • AI replacing jobs • Tech layoffs 2026 • Meta layoffs • Cisco layoffs • Cloudflare layoffs • Coinbase layoffs • Future of software engineering • Artificial intelligence and employment • Automation and workforce changes • Product management careers • Future of work • Tech industry trends #AI #TechLayoffs #ArtificialIntelligence #FutureOfWork #TechJobs #Automation #Meta #SoftwareEngineering #ProductManagement #Technology #CareerAdvice #MachineLearning #Layoffs #TechNews
MNIST: clasifica imágenes con Python desde 0 | Curso ML 2026 #18
🔴 Hoy en directo: tu modelo dice 95% de accuracy... pero está fallando. Te muestro por qué y cómo detectarlo. ⏰ Inicio: martes 26 de mayo · 8:00 PM (GMT-5 / Colombia) 🎯 Qué vas a aprender: - Cargar y explorar el dataset MNIST con scikit-learn - Entrenar tu primer clasificador binario con SGDClassifier - Por qué el accuracy te miente en datasets desbalanceados - Leer e interpretar una matriz de confusión como un profesional - Precisión vs Recall: cuándo importa cada uno y cómo elegir 💎 Hazte miembro del canal para acceder a los lives editados sin pausas y al curso completo: 👉 https://www.youtube.com/channel/UCpqqJGMaVEmyinn1J-DhnYg/join 📂 Recursos del live: - Leer del capitulo 3 del libro Hands-On Machine Learning with Scikit-Learn and PyTorch - Aurélien Géron, lassiguientes secciones: MNIST, Training a Binary Classifier, Performance Measures, Measuring Accuracy Using Cross-Validation and Confusion Matrices. - Documentación scikit-learn: https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.SGDClassifier.html - Dataset MNIST en OpenML: https://www.openml.org/d/554 🔗 Sígueme también en: 💬 Discord 👉 https://discord.gg/NESrnqfNWF 📸 Instagram 👉 https://www.instagram.com/pildoras_de_programacion/ 🎵 TikTok 👉 https://www.tiktok.com/@pil_programacion 📘 Facebook 👉 https://www.facebook.com/pilprogramacion 📺 YouTube 👉 https://www.youtube.com/@pildorasdeprogramacion 🐳 ¡Nos vemos! #machinelearning #python #endirecto #mnist #scikitlearn #clasificacion #matrizdeconfusion #programacion
What Is vLLM? ⚡ Fastest Way to Run AI Models Explained
🚀 In this video, learn What is vLLM and how it helps run Large Language Models (LLMs) faster and more efficiently. We’ll explain: ✅ What vLLM is ✅ How vLLM works ✅ Why it is faster than traditional inference methods ✅ GPU memory optimization with PagedAttention ✅ How to use vLLM for AI applications ✅ vLLM vs Ollama comparison ✅ Best use cases for developers & AI startups vLLM is becoming one of the most popular tools for serving AI models like Llama, DeepSeek, Mistral, and other open-source LLMs. If you're interested in AI, machine learning, ChatGPT alternatives, or self-hosted LLMs, this video is for you! 🔥 📌 Perfect for: AI Developers Python Programmers Machine Learning Engineers GenAI Enthusiasts Odoo & Automation Developers #vLLM #AI #LLM #MachineLearning #ArtificialIntelligence #Python #DeepSeek #Llama3 #GenAI #TechTutorial #OpenSourceAI #AIModels #InferenceEngineWhat Is vLLM? ⚡ Fastest Way to Run AI Models Explained vLLM Explained Simply 🚀 Speed Up Your AI & LLM Inference vLLM Tutorial for Beginners 🔥 Run Large Language Models Faster What Is vLLM and Why Everyone Is Using It? 🤖 vLLM vs Ollama vs LM Studio ⚔️ Best AI Model Runner? How vLLM Makes AI Models Super Fast ⚡ Beginner Guide vLLM Explained in Hindi 🇮🇳 Fast AI Inference Engine Run Llama & DeepSeek Faster with vLLM 🚀 Full Explanation vLLM Setup & Overview 🧠 High-Speed LLM Serving Made Easy Why Developers Love vLLM 💡 AI Model Optimization Explained
Stanford que Ensina Mais sobre LLMs do que a Maioria dos Profissionais de IA
#llm #stanford #chatgpt #inteligenciaartificial #ia Em vez de assistir a uma hora de Netflix, assista a esta palestra de 2 horas da Stanford que vai te ensinar mais sobre como LLMs como ChatGPT e Claude são construídos do que a maioria das pessoas trabalhando em empresas de IA de ponta aprende em suas carreiras inteiras.Essa é uma das aulas mais valiosas que você vai encontrar sobre o funcionamento real dos grandes modelos de linguagem. Direto, profundo e sem enrolação.Se você quer entender de verdade como essas tecnologias são feitas por dentro, essa palestra é ouro puro. Pare o que está fazendo e invista essas 2 horas. Vale muito mais do que parece.Comente: você prefere usar IA ou entender como ela realmente funciona?
Autoencoders - Explained
An autoencoder is a neural network that learns to compress its own input and rebuild it. We start with the impossible-sounding task — squeeze a 49-pixel image down to two numbers and expand it back — then build the hourglass architecture, split it into encoder and decoder, and derive the reconstruction loss that trains the whole thing without a single label. By the end you'll see why the bottleneck is the real trick: forcing the network to carry meaning through a narrow waist is what organises the latent space and turns one idea into denoising, anomaly detection, and generation. *Related Videos* ▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬ Variational Autoencoder - Explained: https://youtu.be/geH5HnRapRs Generative Adversarial Networks (GANs) - Explained: https://youtu.be/G-fXV-o9QV8 Convolutional Neural Networks (CNNs) - Explained: https://youtu.be/YGILT182T6w Recurrent Neural Networks (RNNs) - Explained: https://youtu.be/8G1fImBCMcQ Backpropagation is Just the Chain Rule: https://youtu.be/VCGlYxGJZ04 Activation Functions in Neural Networks - Explained: https://youtu.be/slp222E_0d4 UMAP - Explained: https://youtu.be/kwILqPNZyeo Normalization vs Standardization - Explained: https://youtu.be/87C5hkTY8RI *Contents* ▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬ 00:00 - The Impossible Shortcut 00:22 - The Bottleneck 00:53 - Encoder and Decoder 01:21 - Reconstruction Loss 01:48 - The Latent Space 02:08 - Why This Matters *Follow Me* ▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬ 🐦 X: @datamlistic https://x.com/datamlistic 📸 Instagram: @datamlistic https://www.instagram.com/datamlistic 📱 TikTok: @datamlistic https://www.tiktok.com/@datamlistic 👔 Linkedin: https://www.linkedin.com/company/datamlistic *Channel Support* ▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬ The best way to support the channel is to share the content. ;) If you'd like to also support the channel financially, donating the price of a coffee is always warmly welcomed! (completely optional and voluntary) ► Patreon: https://www.patreon.com/datamlistic ► Bitcoin (BTC): 3C6Pkzyb5CjAUYrJxmpCaaNPVRgRVxxyTq ► Ethereum (ETH): 0x9Ac4eB94386C3e02b96599C05B7a8C71773c9281 ► Cardano (ADA): addr1v95rfxlslfzkvd8sr3exkh7st4qmgj4ywf5zcaxgqgdyunsj5juw5 ► Tether (USDT): 0xeC261d9b2EE4B6997a6a424067af165BAA4afE1a #autoencoders #deeplearning #machinelearning
Diagnóstico de SOP: IA vs medicina tradicional (los datos reales)
7 de cada 10 mujeres con síndrome de ovario poliquístico reciben un diagnóstico erróneo o tardío, pero una nueva red neuronal promete cambiar este panorama clínico radicalmente. La medicina está atravesando un punto de inflexión gracias a la inteligencia artificial aplicada al diagnóstico hormonal. Investigadores han desarrollado un algoritmo capaz de detectar patrones en el SOP que los métodos convencionales pasan por alto. Analizamos cómo el procesamiento de datos a gran escala mejora la precisión clínica, reduciendo años de incertidumbre para las pacientes. Entender esta tecnología no solo es vital para la salud femenina, sino que marca el estándar de la medicina personalizada moderna. 🤖 EN ESTE VÍDEO: ✅ Cómo los algoritmos detectan biomarcadores que la analítica estándar ignora ✅ El papel del machine learning en la reducción de falsos negativos ✅ Comparativa entre el diagnóstico humano y el análisis predictivo por IA ✅ Implicaciones éticas y de privacidad en el manejo de datos médicos sensibles Estamos ante un cambio de paradigma que transformará la atención médica en tiempo récord. Suscríbete para no perderte los avances más disruptivos de la IA y dinos, ¿crees que los algoritmos deberían tener la última palabra en diagnósticos médicos? ▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬ 🔔 SUSCRÍBETE para no perderte ninguna noticia: https://youtube.com/@fjqg?sub_confirmation=1 📡 SÍGUEME EN TODAS LAS REDES: 🌐 Web & blog → https://mybestia.com ▶️ YouTube → https://youtube.com/@fjqg?sub_confirmation=1 📸 Instagram → https://www.instagram.com/quintinogiaia/ 🎵 TikTok → https://www.tiktok.com/@mybestia 💬 Telegram → https://t.me/franciscoquintinogarcia_bot 🦋 Bluesky → https://bsky.app/profile/mybestia.bsky.social 🐘 Mastodon → https://mastodon.social/@mybestia 💼 LinkedIn → https://www.linkedin.com/in/franciscoquintino/ ▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬ 📂 MÁS VÍDEOS DEL CANAL: 🤖 IA y Automatización → https://youtube.com/@fjqg/videos 🔐 Ciberseguridad & Hack → https://youtube.com/@fjqg/videos 📱 Tech y Gadgets → https://youtube.com/@fjqg/videos ⚙️ Desarrollo & Código → https://youtube.com/@fjqg/videos ▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬ 📌 SOBRE MYBESTIA — Francis Quintino Soy Francis Quintino, creador de contenido tech desde Palma de Mallorca 🌴 Especializado en inteligencia artificial, automatización con IA, ciberseguridad, pentesting autónomo, creación de páginas web con IA, e integración de IA en empresas. Todo el contenido de mybestia.com se genera con pipelines de IA propios — sin relleno, sin clickbait, datos reales. ▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬ 🏷️ MYBESTIA, inteligencia artificial, medicina, SOP, síndrome de ovario poliquístico, salud femenina, tecnología, innovación, ciencia, diagnóstico médico, algoritmo, machine learning, salud tech, medicina personalizada, salud 2024, Big Data salud, IA aplicada, ciberseguridad datos, bienestar, avances científicos #IA #SaludTech #SOP #MedicinaPersonalizada #Ciencia #MyBestia
The AI Factory: Engineering Modern LLM Inference Pipelines | Uplatz
Modern AI systems are no longer simple models running isolated predictions—they operate like massive digital factories processing billions of requests, orchestrating GPUs, managing memory, and delivering intelligent responses at global scale. In this video, we explore “The AI Factory” and break down how modern LLM inference pipelines are engineered for performance, scalability, and efficiency. This video is by Uplatz. You’ll learn how large language model inference works behind the scenes, from token generation and request routing to distributed GPU execution and response optimization. We explain why inference engineering has become one of the most critical challenges in the generative AI era. The video dives into core components of modern inference pipelines including model serving, batching strategies, KV cache management, GPU scheduling, vector databases, retrieval-augmented generation (RAG), and low-latency orchestration systems. You’ll understand how organizations optimize infrastructure to reduce inference costs while maintaining performance and responsiveness. We also explore technologies and frameworks used in production AI systems such as Kubernetes, Ray, and vLLM for scalable AI deployment and inference acceleration. Additionally, we discuss concepts like model quantization, mixture-of-experts (MoE) architectures, inference parallelism, autoscaling, observability, and AI infrastructure optimization. Learn how companies engineer AI platforms capable of serving millions of users across enterprise applications, copilots, AI agents, and multimodal systems. Whether you're an AI engineer, platform architect, DevOps professional, cloud engineer, researcher, or technology enthusiast, this video provides a practical and structured understanding of how modern LLM inference factories operate at scale. For full course browse https://uplatz.com/online-courses #LLM #GenerativeAI #AIInfrastructure #MLOps #LLMOps #ArtificialIntelligence #vLLM #GPUComputing #AIEngineering #Uplatz ---------------------------------------------- 🌐 Welcome to Uplatz – Your Gateway to Career Transformation! To access full courses or training bundles: 🌐 https://uplatz.com 📧 support@uplatz.com 🎓 About Uplatz Uplatz is a global leader in online IT and professional training, offering comprehensive courses in AI, machine learning, data science, cloud computing, cybersecurity, and enterprise technologies such as SAP, Oracle, Salesforce, and ServiceNow. With expert-led programs and real-world learning paths, Uplatz empowers learners and organizations across 190+ countries to build future-ready skills and thrive in the digital era. 📘 Explore Uplatz Course Portfolio Learn the most in-demand and emerging technologies with Uplatz: ✅ AI & Machine Learning – Agentic AI, LLMs, LangChain, Deep Learning, MLOps, LLMOps ✅ Cloud & DevOps – AWS, Azure, GCP, Docker, Kubernetes, Terraform, CI/CD ✅ Data & Analytics – Data Science, Data Engineering, Power BI, Tableau, Big Data (Spark, Kafka) ✅ Programming & Frameworks – Python, FastAPI, Django, Java, JavaScript, SQL ✅ Cybersecurity & Blockchain – Ethical Hacking, Cloud Security, Zero Trust, Blockchain & Web3 ✅ IoT & Embedded Systems – IoT Platforms, Edge Computing, Embedded C, Microcontrollers ✅ ERP & CRM – SAP (all modules), Salesforce, Oracle ERP, Microsoft Dynamics ✅ Web & App Development – Full-Stack Development, React, Angular, Node.js, Flutter 🎓 Master cutting-edge skills. Build your tech career with Uplatz. 🌐 Learn more: https://uplatz.com 🎯 Why Choose Uplatz ✔️ Job-focused, project-based learning ✔️ Globally recognized certifications ✔️ Lifetime access & affordable pricing ✔️ Career guidance and mentorship 🔔 Subscribe for weekly tech tutorials, demos, and success stories. 📲 Follow us on LinkedIn, Instagram, Twitter, and Facebook. #Uplatz #Tech #Technology #MachineLearning #CloudComputing #Learning
Anthropic, Claude e a nova corrida da IA: infraestrutura, poder computacional e as polêmicas #218
A disputa pela liderança da inteligência artificial está cada vez mais intensa — e a Anthropic entrou de vez no radar global. Durante o debate, foram levantados pontos sobre o crescimento acelerado da empresa, o impacto do Claude no desenvolvimento de programação, os desafios de infraestrutura computacional e até as polêmicas envolvendo contratos com o Pentágono e big techs. Além da corrida por GPUs e data centers, o grande diferencial parece estar na capacidade de mobilização, arquitetura e escala operacional. Hoje, não basta apenas ter dinheiro ou chips: quem domina a IA precisa ter fornecedores estratégicos, infraestrutura otimizada e capacidade de expansão em tempo recorde. Outro ponto que chamou atenção foi o conceito de “Computer Commitment”, mostrando como IA, hardware, energia, cloud computing e investimentos bilionários estão movimentando um ecossistema inteiro de tecnologia e inovação. Afinal, estamos vendo apenas uma evolução tecnológica… ou o nascimento de uma nova disputa global por poder computacional? 🌎⚡ #InteligenciaArtificial #Anthropic #ClaudeAI #Tecnologia #Inovacao #IA #MachineLearning #OpenAI #CloudComputing #DataCenter #TransformacaoDigital #ValeDoSilicio #BigTech #MercadoTech #FuturoDigital 📢 Nos acompanhe nas redes sociais: 📘 Facebook: https://www.facebook.com/profile.php?id=100090215712870 📷 Instagram: https://www.instagram.com/trendsnewstalks/ 🔗 Linkedin: https://www.linkedin.com/company/trends-news/mycompany/?viewAsMember=true 🎵 Spotify: https://lnkd.in/dKcgxDeE? 🎥 Tiktok: https://www.tiktok.com/@trendsnewstalks
IA Responsable 🤖 | Ética, Transparencia y Uso Seguro de la Inteligencia Artificial
⚠️ La inteligencia artificial está transformando el mundo… pero ¿se está usando de forma correcta? Aquí es donde entra la IA responsable. 🤖📊 En esta MASTERCLASS descubrirás cómo desarrollar y usar sistemas de inteligencia artificial de manera ética, segura y confiable, evitando riesgos y promoviendo el uso adecuado de los datos. 💥 📚 Aprenderás: ▪️ Principios de IA responsable (ética, equidad y transparencia) ▪️ Riesgos de la inteligencia artificial ▪️ Sesgos en los algoritmos ▪️ Protección de datos y privacidad ▪️ Gobernanza de la IA 🎯 Ideal para quienes quieren dominar la inteligencia artificial, gobierno de datos y transformación digital con un enfoque ético. 🚀 Dale play y entiende cómo construir un futuro tecnológico más justo y seguro. #iaresponsable #inteligenciaartificial #eticaia #datagovernance #aiethics #tecnologia #bigdata #privacidad #seguridaddedatos #algoritmos #transformaciondigital #datos #innovacion #cienciadedatos #machinelearning
Why Modern LLMs Use GQA | Multi Query and Grouped Query Attention Visually Explained
Why do modern LLMs like Llama, Qwen, Gemma and Gemini use Grouped-Query Attention (GQA) instead of standard Multi-Head Attention (MHA)? In this video we build a complete intuition for Multi-Query Attention (MQA) and Grouped-Query Attention (GQA), two important transformer attention optimizations used in modern large language models. We understand how KV cache memory and memory bandwidth become major bottlenecks during autoregressive decoding and LLM inference, and why transformer architectures moved toward MQA and GQA attention mechanisms for faster inference and reduced KV cache size. We visually explain Multi-Query Attention, Grouped-Query Attention and the spectrum between MHA, MQA and GQA, including how shared key and value projections work across attention heads. We also compare MQA vs GQA performance, KV cache memory consumption, decoding latency and inference efficiency. The second half of the video focuses on implementation in PyTorch, where we start from a baseline Multi-Head Attention implementation and modify it step-by-step into Multi-Query Attention and Grouped-Query Attention. At the end of the video we go through GQA uptraining techniques proposed for converting existing transformer multi head checkpoints into MQA/GQA models. ⏱️ Timestamps: 00:00 Intro - KV Cache Memory & Bandwidth Bottleneck 02:46 Multi-Query Attention (MQA) Explained 03:57 Intuition for what MQA attention heads learn 06:18 Spectrum of MHA, MQA and GQA 07:48 Grouped-Query Attention (GQA) Explained 09:54 KV Cache Size Comparisons 11:04 MQA vs GQA vs MHA Performance Comparisons 11:51 Baseline Multi-Head Attention (MHA) Implementation 13:40 MQA Implementation in PyTorch 15:51 GQA Implementation in PyTorch 17:54 Uptraining MQA/GQA Models 📖 Resources: MQA Paper - https://arxiv.org/pdf/1911.02150 GQA Paper - https://arxiv.org/pdf/2305.13245 🔔 Subscribe: https://tinyurl.com/exai-channel-link Email - explainingai.official@gmail.com
AI Evals Explained in 3 Steps 🤯 | How Top AI Companies Test Intelligence
Building an AI model is easy now… But proving that it actually works reliably? That’s the real challenge. In this BazAI breakdown, we explore how modern AI evaluation systems work using a simple 3-step framework. This video covers: ✅ Picking the Right AI Task ✅ Collecting Evaluation Datasets ✅ Developing AI Graders We explain how AI companies evaluate: LLMs, RAG systems, coding agents, autonomous AI workflows, reasoning models, safety systems, and multi-agent architectures. You’ll also learn about: 🔹 LLM-as-a-Judge systems 🔹 Human evaluation pipelines 🔹 Code-based grading 🔹 Benchmark datasets 🔹 AI safety testing 🔹 Agent evaluation frameworks As AI becomes more autonomous, evaluation is becoming more important than model size itself. The future of AI belongs to systems that are measurable, reliable, and trustworthy in real-world environments. Subscribe to BazAI for deep AI engineering breakdowns, autonomous agent systems, multimodal AI, and future technology explained simply.