AI Video Producer | Brand & Web Designer for Startups
AI Video Producer | Brand & Web Designer for Startups
I’m an AI & Machine Learning engineer with expertise in deve
- 1x
- Hired
- 6
- Followers
I’m an AI & Machine Learning engineer with expertise in deve
Neuro Lend
My credit model scored 0.92 AUC. Then I changed one field on one applicant, female to male, and she went from approved to rejected. A lot of lending AI works like this: it says no in milliseconds, and nobody, not the customer and often not the bank, can say why. So I built NeuroLend. You fill in a loan application and watch the signal travel through every neuron until the output turns green or red. Then it shows why it decided, and the smallest change that would flip the answer. Rohan is rejected at 54% risk. If he cuts his other EMIs to ₹5,500 a month, or asks for ₹7.5 lakh instead of ₹9 lakh, he's approved.
Here's what's happening underneath. It's a small 8 → 10 → 6 → 1 network trained on 40,000 synthetic Indian loan applications, where I deliberately gave gender zero effect on the outcome. The "why" uses Integrated Gradients against an average applicant instead of raw activations, because glowing neurons look great but explain nothing to a human. Counterfactuals come from a binary search on each input the applicant can actually change, and a fairness check re-scores every applicant with only gender flipped. That check caught the bias that accuracy missed. Retraining with gender cut out of the network dropped the effect to exactly zero, and AUC stayed at 0.92. It all runs in plain JavaScript in the browser, about 0.005 ms per decision, with no server. Code is in the comments. How does your team test lending models for bias today?
Medium - https://medium.com/@anuragnagare77/neuro-lend-99cddd19faad
GitHub - https://github.com/AnuragNagare/Neuro-Lend.git
0
40
One Gate: Voice-controlled Gmail, Calendar, and Drive that can't fire the wrong thing
Every "AI agent" demo shows a voice command turning into a sent email like magic, but almost nobody shows the part that actually matters: what stops it from sending the wrong thing. I built proof: an agent that runs your Gmail, Calendar, Contacts, and Drive by voice reply to a thread, schedule a meeting, archive an email, find a file hands-free end to end, but never fires anything irreversible without you saying so. The honest hard part isn't getting an LLM to sound smart, it's this: a transcript goes to LLM against a strict JSON schema and comes back as an ordered plan, every step tagged reversible or not and exactly one thing in the whole system is allowed to check that flag. Finding a thread, drafting a reply, creating a calendar event: those just run.
The result covers real ground without ever feeling like it's guessing: forward or reply to email with the original quoted underneath, archive/label/trash, resolve a name to a real address through your Contacts first and your mail history as fallback, schedule an event that creates quietly and only emails the invite after a second confirmation, answer "what did John say" or "what's on my calendar Thursday" grounded in content actually fetched from your account not hallucinated. No backend, no server anywhere in the loop
0
90
Everyone's building AR filters and calling it "computer vision magic." Almost nobody's asking what's actually happening underneath — that most of these effects are just clever masking, not detection.
Here's proof. I built an invisibility cloak that runs entirely in the browser, no green screen, no chroma key, no model training.
https://github.com/AnuragNagare/Ghost-frame
4
2
326
What your attention heatmap isn't telling you
Everyone's staring at attention heatmaps and calling it "interpretability." Almost nobody's asking whether a single attention map actually tells you what the model used to make its decision.
It doesn't. Not on its own.
A raw attention map from layer 8 shows you what layer 8 attended to. It says nothing about how that signal got mixed, diluted, or overwritten by every layer before and after it. Attention rollout fixes this — and I built a walkthrough to show why it matters.
Here's what makes it more than a "pretty heatmap" demo:
Instead of visualizing one layer's attention, I traced how information actually flows through the full transformer stack.
→ Every layer's attention matrix is extracted, per head, per token
→ Multi-head attention is averaged, then combined with the residual connection (identity + attention) — this is the step most tutorials skip, and it's the one that actually matters
→ The combined matrices are matrix-multiplied layer by layer, rolling attention forward from input to output
→ The result: a single map showing genuine token-to-token influence across the entire network, not just one layer's snapshot
The overlay shows you everything:
→ Per-layer attention vs. rolled-out attention, side by side
→ Token importance scores overlaid directly on the input text
→ A comparison view: which tokens raw attention says "matter" vs. which ones rollout says actually matter
→ Head-level breakdown so you can see which heads specialize vs. which are noise
No black box. No "trust me, the model looked here." Just linear algebra, applied honestly across every layer instead of cherry-picking one.
Built with PyTorch + HuggingFace Transformers + Matplotlib. Runs on any pretrained transformer, fully offline.
⚠️ Important: attention rollout is an approximation, not ground truth. It assumes attention is the primary information pathway, which ignores MLP layers and can still mislead for very deep models. Treat it as a debugging lens, not proof of causality.
0
197
AI Agent Developer | AI Integration for B2B SaaS
Flutter & full-stack dev shipping AI-powered apps.
Data & AI Governance Consultant | Responsible AI | Power BI
I build AI agents & internal tools that act on data
CUT Coffee — Brew Your Story I reimagined CapCut as a premium coffee brand for creators. The scissors become a cup mark. The timeline becomes a film-strip sleeve. Every great story begins with a cut. Direction A — CapCut as a Different Industry
https://www.linkedin.com/posts/abuaasif_capcutdesignstudio-branddesign-capcut-activity-7467333219772952576-53vt?utm_source=share&utm_medium=member_desktop&rcm=ACoAACRm5rcB0nVG0_HUX6-IXfuWqNGquZ-jMQU
0
602
Tech solutions with a product-first approach.
Tech solutions with a product-first approach.
View more →
AI Automation & Workflow Solutions for Businesses
AI Content Creator — Python & Streamlit Prototype
A personal learning project developed with AI assistance using Python, Streamlit and the Gemini API. The source implements a topic field, five content formats (LinkedIn post, Instagram caption, Twitter post, professional email and blog outline) and four tone choices. It builds a prompt from those selections and displays the model response.
The image shows my actual public source code. The previous live deployment is currently unavailable; this portfolio item documents the prototype rather than a currently working hosted service.
Code: https://github.com/Mohammed905-stack/ai-content-creator
0
37
AI Shipping BL Auditor — CargoDoc AI
A personal shipping-document prototype developed with AI assistance, combining my EXIM learning with Python, Streamlit, pypdf and Gemini. It extracts text from PDF Bills of Lading, commercial invoices and packing lists, then prompts the model to identify document details, packaging remarks, weight discrepancies and Incoterm issues. It also includes a built-in test sample.
The image shows my actual deployed interface. The model-generated findings are intended for human review.
App: https://kaderji-cargo-auditor.streamlit.app/
(https://kaderji-cargo-auditor.streamlit.app/)Code: https://github.com/Mohammed905-stack/ai-shipping-bl-auditor
0
40
Express Docs — Technical Documentation RAG Assistant
A personal project developed with AI assistance. It answers questions from five official FastAPI guides using Python, LangGraph, Gemini and FAISS. It includes source citations, relevance checks, bounded retrieval retries, a visible decision trace and SQLite feedback storage. Questions outside the source material are refused.
This is a screenshot from my real local demo.
Code: https://github.com/Mohammed905-stack/express-analytics-rag-assistant
0
42
