Building an AI-Powered Learning Navigator: The Blueprint for Hyper-Personalized Education | Eastside Entrepreneurs .
Sign in

Members-Only

Recent Talks & Demos are for members only

Exclusive feed

You must be an AI Tinkerers active member to view these talks and demos.

Sign in View FAQ
December 05, 2025 · Eastside Entrepreneurs

AceRocket: AI Learning Navigator

Learn how an AI learning navigator addresses student gaps, adapts practice in real time, and the practical lessons learned from gaining early traction in the Eastside community.

TensorFlow Machine Learning Adaptive Learning Content Pipeline PyTorch scikit-learn Keras GPT-4 GPT-3 BERT ONNX
Overview

AceRocket is an AI-powered learning navigator designed to help high school students master math with clarity, confidence, and consistency. Unlike traditional test prep which relies on static worksheets, long videos, or expensive tutoring — AceRocket provides a dynamic, personalized practice system driven by AI and real performance data.

In my presentation, I will introduce:

  • What problem AceRocket solves: students feel lost, parents lack visibility, and traditional prep tools do not adapt to individual gaps.
  • How our Triple-A Learning Cycle (Active, Adaptive, AI-powered) guides students through daily personalized practice that adjusts in real time.
  • Early traction from local Eastside students, parents, and educators.
  • Our business model and our plan to scale from math exams into broader AI-driven learning guidance and workforce training.

The talk will give the audience a clear understanding of AceRocket’s value, technology, and our roadmap toward becoming the “AI learning GPS” for millions of learners.

Links
Tech stack
  • TensorFlow
    Google's open-source, end-to-end platform for building, training, and deploying machine learning models across all environments.
    TensorFlow is the open-source, end-to-end machine learning platform developed by the Google Brain team . It provides a comprehensive ecosystem of tools for model development: Keras simplifies high-level neural network construction, and TensorBoard offers visualization and debugging . The framework is engineered for scalability, supporting distributed training on powerful hardware like Google's custom Tensor Processing Units (TPUs) . Crucially, its ecosystem—including TensorFlow Lite for mobile/edge devices and TensorFlow.js for web browsers—ensures deployment flexibility, allowing models to run on servers, microcontrollers, or directly in a browser .
  • Machine Learning
    Compute dense vector representations for sentences and paragraphs using a Python framework that optimizes transformer models for semantic similarity.
    Sentence Transformers (SBERT) maps variable-length text into fixed-size, high-dimensional vectors to enable high-speed semantic analysis. The framework fine-tunes architectures like BERT using Siamese and Triplet network structures: this ensures semantically similar inputs cluster together in vector space. This methodology powers critical NLP tasks: semantic search, clustering, and paraphrase detection. Standard models (like all-MiniLM-L6-v2) provide a 384-dimensional baseline for real-time applications, while larger variants (such as all-mpnet-base-v2) offer superior accuracy for complex information retrieval.
  • Adaptive Learning
    Data-driven algorithms recalibrate educational content in real-time to match individual student mastery levels.
    Adaptive learning transforms static curriculum into dynamic pathways by analyzing student performance data through platforms like McGraw Hill Connect or DreamBox Learning. The system monitors specific metrics (response time, accuracy, and confidence levels) to adjust the difficulty and sequence of material instantly. If a student struggles with algebraic functions, the software pivots to foundational scaffolding; if they excel, it accelerates them to complex modeling. This precision engineering reduces training time by up to 50% in corporate settings and significantly closes achievement gaps in K-12 classrooms.
  • Content Pipeline
    A high-performance build system that compiles raw creative assets into optimized, platform-ready binary formats.
    Content Pipeline automates the heavy lifting of game development by transforming source files (FBX models, WAV audio, and PNG textures) into lean, runtime-efficient XNB files. It leverages a multi-stage process of importing, processing, and compiling to ensure assets are compressed and formatted for specific hardware targets like Xbox or PC. By decoupling raw design files from the final executable, it reduces memory overhead and accelerates load times across the entire build.
  • PyTorch
    PyTorch is the open-source machine learning framework: it provides a Python-first tensor library with strong GPU acceleration and a dynamic computation graph for building deep neural networks.
    PyTorch, developed by Meta AI, is a premier open-source deep learning framework favored in both research and production environments. Its core is a powerful tensor library (like NumPy) optimized for GPU acceleration, delivering 50x or greater speedups for complex computations. The key differentiator is its 'Pythonic' design and dynamic computation graph (eager execution), which allows for rapid prototyping and simplified debugging compared to static-graph frameworks. Leveraging its Autograd system for automatic differentiation, practitioners build and train models for computer vision and NLP; major companies like Tesla (Autopilot) and Microsoft utilize PyTorch for critical AI applications.
  • scikit-learn
    Scikit-learn (sklearn) is the essential Python library for efficient, production-ready machine learning, built on NumPy and SciPy.
    Scikit-learn (sklearn) is the industry-standard Python library, providing a unified API for efficient predictive data analysis. It delivers robust, open-source implementations of core machine learning algorithms: classification (e.g., Support Vector Machines, Random Forests), regression (e.g., Linear Regression), and clustering (K-Means, DBSCAN). Built on the foundational scientific stack (NumPy, SciPy), its consistent Estimator API simplifies complex data science workflows. Developers use it to quickly move from data preprocessing (StandardScaler) to model evaluation (accuracy_score) and pipeline construction in production environments.
  • Keras
    Keras is a multi-framework deep learning API (written in Python) that runs on top of JAX, TensorFlow, or PyTorch.
    Keras 3 is the multi-framework deep learning API, designed for human-centric development: it focuses on reducing cognitive load and enabling fast experimentation. It provides a simple, consistent interface for building models, from basic Sequential stacks to complex Functional API architectures. The framework offers industry-strength performance and scalability, leveraging backends like JAX for optimized training on GPUs and TPUs. Organizations like NASA, YouTube, and Waymo utilize Keras for production-grade applications, proving its power and reliability across computer vision and NLP domains.
  • GPT-4
    GPT-4 is OpenAI’s large multimodal model: it processes both text and image inputs, delivering human-level performance on complex professional and academic benchmarks.
    This is OpenAI’s latest milestone in scaling deep learning: a large multimodal model accepting both text and image inputs. It demonstrates a significant capability leap over its predecessor, scoring in the top 10% on a simulated bar exam (GPT-3.5 scored in the bottom 10%). The model handles nuanced instructions and long-form content, supporting context windows up to 32,768 tokens (32K model). This capacity allows processing up to 25,000 words in a single, complex prompt. GPT-4 is engineered for enhanced reliability, steerability, and advanced reasoning across diverse tasks.
  • GPT-3
    A 175-billion parameter autoregressive language model that masters complex tasks through few-shot learning.
    OpenAI debuted GPT-3 in 2020: a transformer-based engine trained on 570GB of filtered text. It utilizes 175 billion parameters to execute diverse functions (including Python scripting and logical reasoning) using only natural language prompts. This architecture removed the requirement for task-specific fine-tuning: establishing the foundation for modern tools like GitHub Copilot and the initial ChatGPT release.
  • BERT
    BERT (Bidirectional Encoder Representations from Transformers) is a foundational, pre-trained NLP model that uses a Transformer encoder to process text bidirectionally, capturing full word context for superior language understanding.
    BERT is a revolutionary language representation model introduced by Google AI Language in 2018. It is built on the Transformer architecture and distinguishes itself by being deeply bidirectional: it processes the entire sequence of words (left and right context) simultaneously, unlike previous unidirectional models. This capability is achieved through a Masked Language Model (MLM) pre-training objective. The model, released in sizes like BERTBASE (110 million parameters) and BERTLARGE (340 million parameters), dramatically improved the state-of-the-art across 11+ Natural Language Processing tasks, including question answering (SQuAD) and sentiment analysis, establishing a new baseline for the field.
  • ONNX
    ONNX (Open Neural Network Exchange) is an open-source format: it standardizes machine learning models, ensuring interoperability across all major frameworks and deployment hardware.
    ONNX delivers critical model portability. It defines a standardized computation graph and operator set, allowing developers to train a model in one framework (e.g., PyTorch or TensorFlow) and deploy it seamlessly using a different runtime. This eliminates framework lock-in and optimizes production performance. Founded in 2017 by key industry players (AWS, Microsoft, Facebook), ONNX now boasts contributions from companies like NVIDIA, Intel, and Qualcomm. The high-performance ONNX Runtime, for example, powers AI inference across major Microsoft products, including Windows, Office, and Azure Cognitive Services, demonstrating its enterprise-grade efficiency and cross-platform capability (cloud, edge, mobile).

Related projects

Bootstrapping AI To Success

Seattle

Learn how we built the AI Game Master from concept to revenue, detailing model choices, infrastructure decisions, and…

Just show up

Eastside Entrepreneurs

A personal account of a child's rare brain condition, the resilience lessons learned, and how they guided scaling…

How Does Rocket Science Relate to Every Industry? And More Rantings from a Former Rocket Scientist

Eastside Entrepreneurs

This talk explores key lessons from rocket science, engineering, and manufacturing that can be applied to improve processes…

CEO

Eastside Entrepreneurs

Explore how AI-powered legal software streamlines compliance, reduces costs, and improves decision‑making for law firms, hospitals, school districts,…

CEO

Eastside Entrepreneurs

This talk explores how AI can transform traditional numeric feedback into meaningful conversations, improving the accuracy and depth…

Viewpoint.AI accelerated augmentation of individual and complex group decisions, by 10-1000x, Fully transparent, continuously curated by humans, delivering optimal results fro Finech, Legal, Education, Aerospace, IT, Governement and more.

Eastside Entrepreneurs

Learn how Viewpoint AI builds transparent digital decision models, accelerates complex group decisions, and preserves expert knowledge for…

Events Gallery