{"id":51351173,"url":"https://github.com/hassanalgoz/aai","last_synced_at":"2026-07-02T16:03:44.893Z","repository":{"id":329274438,"uuid":"1117675751","full_name":"HassanAlgoz/AAI","owner":"HassanAlgoz","description":"AAI is an 8-week bootcamp for programmers to build AI software.","archived":false,"fork":false,"pushed_at":"2026-07-02T12:54:30.000Z","size":192504,"stargazers_count":5,"open_issues_count":0,"forks_count":52,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-07-02T14:23:27.076Z","etag":null,"topics":["agneticai","artificial-intelligence","bootcamp","course"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/HassanAlgoz.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":"AGENTS.md","dco":null,"cla":null}},"created_at":"2025-12-16T16:47:02.000Z","updated_at":"2026-07-02T12:55:08.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/HassanAlgoz/AAI","commit_stats":null,"previous_names":["hassanalgoz/b5","hassanalgoz/aai"],"tags_count":4,"template":false,"template_full_name":null,"purl":"pkg:github/HassanAlgoz/AAI","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/HassanAlgoz%2FAAI","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/HassanAlgoz%2FAAI/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/HassanAlgoz%2FAAI/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/HassanAlgoz%2FAAI/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/HassanAlgoz","download_url":"https://codeload.github.com/HassanAlgoz/AAI/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/HassanAlgoz%2FAAI/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":35053497,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-07-02T02:00:06.368Z","response_time":173,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["agneticai","artificial-intelligence","bootcamp","course"],"created_at":"2026-07-02T16:03:44.000Z","updated_at":"2026-07-02T16:03:44.879Z","avatar_url":"https://github.com/HassanAlgoz.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Applied Artifical Intelligence (AAI)\n\nWelcome: [introduction to the Applied Artificial Intelligence Bootcamp](https://github.com/HassanAlgoz/AAI/releases/latest/download/Intro_01_bootcamp_intro.pdf) (1hr 30m).\n\nPDF material can be downloaded from the [releases page](https://github.com/HassanAlgoz/AAI/releases).\n\nThe program consists of two tracks each aimed at a specific career path:\n\n1. Data Scientist\n2. AI Engineer\n\n## Pre-requisites\n\nBoth tracks presume the following about the learner to get started:\n\n+ English B2 (Upper-Intermediate) level: IELTS 6.5 or TOEFL 80.\n+ Algorithmic thinking and problem-solving skills.\n+ Strong foundation in programming.\n+ Working laptop with internet access.\n\n### 1. [Terminal](/courses/Terminal/)\n\nCommand and conquer your machine. Fear not the black box. Protect yourself from malicious code.\n\nTime Estimate: 1 day x 3 hours.\n\n## Track 1: Data Scientist\n\nTime Estimate: 4-5 weeks at 30 hrs/week.\n\n### 1. [Data Wrangling](/courses/Data_Wrangling/)\n\nFundamentals of data wrangling and analysis in Python via pandas, matplotlib and seaborn.\n\n- M1. Filtering, Sorting, and Aggregation\n- M2. Data Wrangling\n- M3. Data Vizualization\n- M4. Timeseries Analysis\n\nTime Estimate: 5 days x 6 hours.\n\n### 2. [Data Science](/courses/Data_Science/)\n\nCalculate, analyze, visualize, and extract insights from data. Formulate hypotheses and draw conclusions.\n\n- M1. Introductions\n- M2. Univariate Analysis\n- M3. Bivariate Analysis\n- M4. Inferential Statistics\n\nTime Estimate: 5 days x 6 hours.\n\n### 3. [Applied Machine Learning](/courses/Machine_Learning/)\n\nBuild reliable predictive modeling pipelines, debug its issues, evaluate and compare alternatives.\n\n- M1. Supervised ML: Regression and Classification\n- M2. Estimating and Improving Model Generalization Performance\n- M3. Pipeline: Building Reliable Predictive Models\n- M4. Decision Trees and Ensembles\n- M5. AutoML\n\nTime Estimate: 10 days x 6 hours.\n\n## Track 2: AI Engineer\n\nTime Estimate: 4-5 weeks at 30 hrs/week.\n\n### 1. [Agentic Engineering](/courses/Agentic_Engineering/)\n\nWork effectively and efficiently with AI in software engineering projects.\n\n- M1. From Vibe Coding to Agentic Engineering\n- M2. Skills for Engineers\n- M3. Agent Modes\n\nTime Estimate: 5 days x 6 hours.\n\n### 2. [Building Agentic AI Software](/courses/Agentic_AI/)\n\nDevelop, debug, evaluate, deploy, and monitor LLM-driven AI Agents to automate tasks involving unstructured data.\n\n- M1. Signatures and Modules\n- M2. Agents with Tools\n- M3. Coding Agents\n- M4. Optimization\n- M5. Retrieval Augmented Generation (RAG)\n\nTime Estimate: 10 days x 6 hours.\n\n### 3. [Applied Deep Learning](/courses/Deep_Learning/)\n\nSelect, use, compose, fine-tune, and deploy open-weight deep learning models on various unstructured data tasks.\n\n- M1. HuggingFace and Large Language Models\n- M2. Realtime Computer Vision Models\n\nTime Estimate: 5 days x 6 hours.\n\n## AI Policy\n\nGood use of AI means it **augments, rather than replaces, thinking** — used for feedback, hints, explanations, practice, or extra resources, while **you still do the core reasoning, writing, and problem-solving**.\n\n**Forbidden use**: treating course material as \"work\" and AI as an assistant to get it done \"faster\" or \"easier\" or \"better\". Don't mix productivity (output) with learning (you).\n\nSee [the research and findings that made up our AI Policy](docs/ai_policy.md).\n\n## Assigned Exercises\n\n- Due Thursday 11:59 PM (end of same week).\n- Work must have been pushed to GitHub.\n- Marked as done (in Google Classroom) before then.\n- Commit history **MUST** follow the [proof-of-work](/docs/proof-of-work.md) system.\n\n---\n\n## Contribution (Course Development)\n\n- Local dev unchanged: `just compile` / `just watch` still produce ignored local PDFs.\n- To publish: `git tag v1.0 \u0026\u0026 git push origin v1.0` -\u003e workflow builds and attaches PDFs to the v1.0 release, which becomes latest.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhassanalgoz%2Faai","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhassanalgoz%2Faai","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhassanalgoz%2Faai/lists"}