Skip to content
View Ayai1's full-sized avatar

Block or report Ayai1

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Ayai1/README.md

Syed Ayaan Ahmed

Final-year B.Tech CSE (AI & ML) at Woxsen University, Hyderabad. I build deep learning systems end to end — data, training, honest evaluation, and the part where somebody else can actually run it.

Currently building atlas — a local-first AI companion that diagnoses and explains your machine without sending a byte of it anywhere.


Selected work

Project What it does Where it got to
AI-Generated Image Detection EfficientNet-B0 classifier for DALL·E / Midjourney / SDXL output, with Grad-CAM to show what the model keyed on 98.5% on held-out test images, trained on 120k
atlas Local-first, privacy-first assistant that diagnoses system problems and explains them in plain language. Runs fully on-device — no telemetry, no cloud In active development
Continual learning with DCE-CVAE Class-incremental learning on Split-MNIST via pure latent replay — four-tier memory hierarchy, per-task orthogonal subspaces, latent merging ≈0.66 avg accuracy over 5 sequential tasks vs ≈0.20 for naive fine-tuning
symptoms-disease-reasoning Diagnostic reasoning engine: rule-based scoring, ML ensemble priors, Tree-of-Thoughts questioning, and RAG explanations grounded in PubMed Research prototype, interactive CLI + API
autostream-ai-agent LangGraph agent that turns a conversation into a qualified lead — passive field extraction, confidence-thresholded intent routing, RAG-grounded replies Deployable to WhatsApp via webhooks
multimodal-market-signal-fusion Audio sentiment + TF-IDF text + technical indicators, fused with entropy-based adaptive gating and XGBoost 0.627 acc / 0.616 F1 — under a leak-free chronological split, not a shuffled one

Tools

Python · PyTorch · TensorFlow · scikit-learn · Transformers · LangChain · LangGraph · XGBoost · OpenCV · FastAPI · Ollama · C++

Interests

Computer vision and object detection · continual learning · retrieval-augmented and agentic systems · on-device and privacy-preserving ML — and increasingly the product side of all of it: what to build and why, not just how.

Reach me

LinkedIn · saayaan1208@gmail.com

Pinned Loading

  1. AI-Generated-Image-Detection-Using-EfficientNet-B0 AI-Generated-Image-Detection-Using-EfficientNet-B0 Public

    AI Generated Image detection using a lightweight, highly accurate deep learning model. Trained on dataset with over 120k images from various sources like DALL-E,Midjourney,SDXL, etc.

    Jupyter Notebook 1

  2. multimodal-market-signal-fusion multimodal-market-signal-fusion Public

    Multimodal ML pipeline combining audio features, TF-IDF text embeddings, and market technical indicators using entropy-based adaptive gating and XGBoost fusion.

    Python

  3. symptoms-disease-reasoning symptoms-disease-reasoning Public

    Hybrid AI medical reasoning system combining rule-based scoring, ML ensemble priors, Tree-of-Thoughts questioning, and RAG-based explainability.

    Python 1

  4. autostream-ai-agent autostream-ai-agent Public

    AI agent based on langchain to convert user conversations into leads with RAG and intent-aware flow.

    Python

  5. atlas atlas Public

    A local-first AI companion for your computer - diagnoses system and dev-environment problems and explains them in plain language. Runs entirely on-device via Ollama: no telemetry, no cloud, no data…

    Python

  6. continual-learning-dce-cvae continual-learning-dce-cvae Public

    Class-incremental continual learning on Split-MNIST using pure latent replay - a DCE-CVAE backbone with a four-tier memory hierarchy and per-task orthogonal latent subspaces. Replays compressed lat…

    Python