📰 Dev.to · Jashwanth
Articles from Dev.to · Jashwanth · 24 articles · Updated every 3 hours · View all reads
All
⚡ AI Lessons (9097)
ArXiv cs.AIDev.to · FORUM WEBForbes InnovationOpenAI NewsDev.to AIHugging Face Blog
Dev.to · Jashwanth
2w ago
SmartKNN vs Classical KNN: Regression Benchmark Results
It’s been a while since I revisited KNN-style models for regression, so I decided to run a clean...
Dev.to · Jashwanth
3w ago
What It Actually Takes to Build a Production-Ready ML Model
Most ML tutorials end like this: Model trained successfully And everyone claps… Meanwhile in...
Dev.to · Jashwanth
1mo ago
SmartKNN v0.2.3 Released
SmartKNN v0.2.3 Released - Stability, Performance, and Global Distance Improvements I’m excited to...
Dev.to · Jashwanth
1mo ago
I Benchmarked 8 ML Models on CPU (No Tuning, No Tricks). Here’s What Happened
What I Did All models were tested under the same rules: Default settings from their libraries No...
Dev.to · Jashwanth
1mo ago
Will GBMs Still Dominate Tabular Data for the Next Decade?
Gradient Boosting Machines (GBMs) have become the dominant approach for tabular data because they...
Dev.to · Jashwanth
2mo ago
What If India Built Its Own Cloud, Chips, and LLMs?
(A not-so-crazy thought experiment) “What if India stopped renting the internet… and started owning...
Dev.to · Jashwanth
2mo ago
A New Direction in Classification at SmartEco
At SmartEco, we’ve been exploring an alternative direction to traditional tree-based and...
Dev.to · Jashwanth
2mo ago
SmartKNN v2.2: Improving Scalability, Correctness, and Training Speed
SmartKNN v2.2 is a focused update aimed at making the library more scalable, predictable, and...
Dev.to · Jashwanth
2mo ago
Product Quantization: How ANN Systems Cheat Distance Without Breaking Search
If you’ve ever built or used an Approximate Nearest Neighbor (ANN) system at scale, you already know...
Dev.to · Jashwanth
2mo ago
The ACCURACY- INFERENCE - MEMORY Triangle in ML Systems
Most ML discussions obsess over accuracy. Production systems don’t. In real systems, models live...
Dev.to · Jashwanth
2mo ago
We’ve Been Building an ANN Engine for Six Months. Here’s Where It Stands.
About six months ago, we started experimenting with an idea for an approximate nearest neighbor (ANN)...
Dev.to · Jashwanth
2mo ago
I Pitted AutoML Against a Single Model. The Results Were Uncomfortable
What Is AutoML? AutoML systems, such as H2O AutoML, are designed to automate the process...
Dev.to · Jashwanth
2mo ago
What SmartML Benchmarks Tell You Before Hyperparameter Tuning
In most ML blogs and tutorials, benchmarks look like this: Tune forever → squeeze the last 0.1% →...
Dev.to · Jashwanth
3mo ago
Production ML is not about models. It’s about trade-offs.
In tutorials, ML looks simple: train a model → get accuracy → ship. In production, none of that...
Dev.to · Jashwanth
3mo ago
Why I Built a Dedicated Benchmarking System
Over the past few months, I’ve been working on large-scale benchmarks for SmartKNN. What I didn’t...
Dev.to · Jashwanth
3mo ago
Happy New Year 2026: An Algorithmic Guide to ML Models
Strengths, Weaknesses, Trade-offs, and When to Use What (2026 Edition) First of all -...
Dev.to · Jashwanth
3mo ago
SmartKNN Regression Benchmarks High-Dimensional Datasets
This release presents initial regression benchmarks for SmartKNN, evaluated on large-D datasets with...
Dev.to · Jashwanth
3mo ago
SmartKNN - Large Scale Classification Benchmarks (CPU)
This release presents initial classification benchmarks for SmartKNN, evaluated on million-scale...
Dev.to · Jashwanth
3mo ago
SmartKNN v2 Is Here - Low-Latency, Scalable, and Built for Real-World ML
After months of deep engineering, redesigns, and painful benchmarking, SmartKNN v2 (v0.2.0) is...
Dev.to · Jashwanth
3mo ago
Ever Wondered Why So Many ML Algorithms Exist - Even When Big Names Dominate?
If machine learning had a single “best” algorithm, the field would be boring by now. Yet even today,...
Dev.to · Jashwanth
3mo ago
A Small Milestone While Building SmartKNN
Over the past few weeks, I’ve been building SmartKNN - a practical take on the classic K-Nearest...
Dev.to · Jashwanth
4mo ago
How SmartKNN Learns Feature Weights Internally.
“KNN secretly behaves like metric learning once you stop being lazy with distances.” KNN is famous...
Dev.to · Jashwanth
4mo ago
SmartKNN Regression Benchmarks — How Far Can a Smarter KNN Really Go?
Over the past weeks, we benchmarked SmartKNN against KNN, SVR, Decision Tree Regression, Random...
Dev.to · Jashwanth
4mo ago
SmartKNN: An Interpretable Weighted Distance Framework for K-Nearest Neighbours
SmartKNN vs Weighted_KNN & KNN: A Practical Benchmark on Real Regression...
DeepCamp AI