note

Half of Data Cleansing Cannot Be Solved with Code—Outliers and Domain Knowledge

When you run machine learning code, you sometimes get results like this. "This sample is an outlier." An algorithm called Isolation Forest identified 3 out of 50 experimental data points as "anomalies ...
note

Mythos-nano: A Deep Dive into the 'Ultimate Inference in Small-Scale Models' Proven by 3B Parameters, Focused Entirely on Math, Code, and Logic

I'm currently looking into this after catching wind of the claim that it's the successor to VibeThinker-3B. This is the non-1-bit quantized version of the model I posted about earlier. I completely ...
Communications of the ACM

The LLVM Compiler Infrastructure

LLVM powers the core development tools, operating systems, and most applications at Apple Computer, where it long ago ...
GitHub

sales-data

End-to-end demand forecasting with Python using synthetic time-series sales data. Includes data generation, cleaning, ARIMA/SARIMA model selection by AIC, evaluation with RMSE and MAPE, and 90-day ...
GitHub

Microsoft.Diagnostics.Runtime

Microsoft.Diagnostics.Runtime.dll also called "ClrMD" is a process and crash dump introspection library. This allows you to write tools and debugger plugins which can do thing similar to SOS and ...