AI Skills

🔗 Harbor — a local stack for working with LLM in one click. This tool simplifies launching local language models and related services — from web interfaces to RAG and voice interaction. Everything runs in Docker and is configured with a couple of commands. Harbor automatically integrates components, for example, SearXNG is immediately connected to Open WebUI for web search, and ComfyUI — for image generation. Suitable for those who want to quickly deploy a local environment for AI experiments. 🔗 GitHub

🔅 Building AI Applications with Amazon Bedrock 🌐 Author: Noah Gift 🔰 Level: Intermediate ⏰ Duration: 1h 7m

🌀 Learn how to build real-world AI applications using Amazon Bedrock.

📗 Topics: Amazon Bedrock, Artificial Intelligence, Application Development 📤 Join Artificial intelligence for more courses

📂 Full description In this course, learn how to build real-world, AI-powered applications using Amazon Bedrock. Instructor Noah Gift starts off with an examination of the foundation model service, focusing on how to utilize the unified API to interact with various foundational models, such as those from Anthropic, Amazon's own models, or Mistral. He compares different variants and demonstrates how to effectively employ this unified interface. Then, dive into the console and explore its significance and advantages for prototyping. Noah then guides you through building applications, showing how to use the chat interface and compare different prompts, and explains the agents ecosystem. Plus, learn how to use the knowledge base, including how to ground using retrieval, augmented generative AI, and how to combine these elements. Note: This course was created by Pragmatic AI Labs. We are pleased to host this training in our library.

📈 METR: AI is starting its own "Moore's Law" When will AI be able to independently complete long projects? Researchers from METR found a pattern: the time horizon of tasks that AI agents can handle doubles every ~7 months. Now they tested this on 9 new benchmarks: MATH, OSWorld, LiveCodeBench, Mock AIME, GPQA Diamond, Tesla FSD, Video-MME, RLBench, and SWE-Bench Verified. Results: 🧠 Similar growth rates in science, math, robotics, programming, and even autopilot. ⚡️ New models like o3 grow faster than predicted — median doubling now ~4 months. 🕐 On reasoning tasks, agents last 1+ hour. 🖱 But in OS and browser — still about ~2 minutes, due to weak tools. > "Moore's Law for AI": not about chips — about the ability to think and work longer. Faster. Independently. AI agents grow not by days, but by benchmarks.

Key Concepts for Machine Learning Interviews 1. Supervised Learning: Understand the basics of supervised learning, where models are trained on labeled data. Key algorithms include Linear Regression, Logistic Regression, Support Vector Machines (SVMs), k-Nearest Neighbors (k-NN), Decision Trees, and Random Forests. 2. Unsupervised Learning: Learn unsupervised learning techniques that work with unlabeled data. Familiarize yourself with algorithms like k-Means Clustering, Hierarchical Clustering, Principal Component Analysis (PCA), and t-SNE. 3. Model Evaluation Metrics: Know how to evaluate models using metrics such as accuracy, precision, recall, F1 score, ROC-AUC, mean squared error (MSE), and R-squared. Understand when to use each metric based on the problem at hand. 4. Overfitting and Underfitting: Grasp the concepts of overfitting and underfitting, and know how to address them through techniques like cross-validation, regularization (L1, L2), and pruning in decision trees. 5. Feature Engineering: Master the art of creating new features from raw data to improve model performance. Techniques include one-hot encoding, feature scaling, polynomial features, and feature selection methods like Recursive Feature Elimination (RFE). 6. Hyperparameter Tuning: Learn how to optimize model performance by tuning hyperparameters using techniques like Grid Search, Random Search, and Bayesian Optimization. 7. Ensemble Methods: Understand ensemble learning techniques that combine multiple models to improve accuracy. Key methods include Bagging (e.g., Random Forests), Boosting (e.g., AdaBoost, XGBoost, Gradient Boosting), and Stacking. 8. Neural Networks and Deep Learning: Get familiar with the basics of neural networks, including activation functions, backpropagation, and gradient descent. Learn about deep learning architectures like Convolutional Neural Networks (CNNs) for image data and Recurrent Neural Networks (RNNs) for sequential data. 9. Natural Language Processing (NLP): Understand key NLP techniques such as tokenization, stemming, and lemmatization, as well as advanced topics like word embeddings (e.g., Word2Vec, GloVe), transformers (e.g., BERT, GPT), and sentiment analysis. 10. Dimensionality Reduction: Learn how to reduce the number of features in a dataset while preserving as much information as possible. Techniques include PCA, Singular Value Decomposition (SVD), and Feature Importance methods. 11. Reinforcement Learning: Gain a basic understanding of reinforcement learning, where agents learn to make decisions by receiving rewards or penalties. Familiarize yourself with concepts like Markov Decision Processes (MDPs), Q-learning, and policy gradients. 12. Big Data and Scalable Machine Learning: Learn how to handle large datasets and scale machine learning algorithms using tools like Apache Spark, Hadoop, and distributed frameworks for training models on big data. 13. Model Deployment and Monitoring: Understand how to deploy machine learning models into production environments and monitor their performance over time. Familiarize yourself with tools and platforms like TensorFlow Serving, AWS SageMaker, Docker, and Flask for model deployment. 14. Ethics in Machine Learning: Be aware of the ethical implications of machine learning, including issues related to bias, fairness, transparency, and accountability. Understand the importance of creating models that are not only accurate but also ethically sound. 15. Bayesian Inference: Learn about Bayesian methods in machine learning, which involve updating the probability of a hypothesis as more evidence becomes available. Key concepts include Bayes’ theorem, prior and posterior distributions, and Bayesian networks.