TildAlice – Tech Blog for Developers
Python, AI, Deep Learning, Data Analysis, Computer Vision, Reinforcement Learning โ tips and tutorials
Latest Posts
-
Attention Is All You Need: Transformer Architecture Review
Attention Is All You Need dismantled: why self-attention replaced RNNs, how positional encoding works, and the 3 tricks that made it scale.
-
Real-time Whisper Is a Battery Nightmare (Here’s How to Fix It)
Real-time Whisper drains 1% battery/min. VAD + adaptive inference + thermal throttling bring it down to 0.2%. Benchmarks on iPhone 13 Pro.
-
Hybrid Search for RAG: BM25 + Vector Search Combined
Hybrid search boosts RAG recall 35% over vector-only. Combine BM25 + embeddings with rank fusionโPython code, real datasets, ablation results.
-
Top 10 Python Interview Algorithms: BFS to DP
Master 10 interview algorithms fast: BFS, DFS, DP, binary search. Python templates, complexity cheat sheet, and the 3 patterns that solve 80%.
-
On-Device Whisper: ONNX and Core ML Inference Guide
ONNX Runtime + CoreML beats native Core ML for Whisper on iOS by 40%. Conversion script, memory pool tricks, and A15/A16 benchmark numbers.
-
7 Python Interview Patterns: Two Pointers to Sliding Window
Stop memorizing LeetCode solutions. Master 7 interview patterns that solve 80% of algorithm questions โ with O(n) complexity breakdowns.
-
Multi-Agent RL Guide: Cooperative and Competitive Learning
QMIX vs self-play: benchmarked 3 MARL algorithms on StarCraft micromanagement. One approach dominated cooperative tasks, the other competitive.
-
Attention-Based Sensor Fusion: 15% Better Pump Failure Prediction
Fusing vibration, temperature, and current sensors with Attention boosted pump failure prediction from 79% to 94.2% โ here's the architecture.