Deep Diaries · 10 posts, 2023 to 2026
The writing map.
Posts are the dots, topics are the diamonds. Tap a node to preview it, drag to rearrange, or ask a question and watch the posts it was drawn from light up. Every post is reproduced in full on this site, equations and figures included.
All posts
- Rethinking How AI Learns: Why Backpropagation Doesn't Quite Match the BrainA look at new research on the structural differences between deep neural networks and human visual processing.
- Focus Unfolded: A Deep Dive into Attention Mechanisms in AIFrom Singular Focus to Multifaceted Insight: Exploring Attention, Self-Attention, and Multi-Head Attention
- Exploring YOLOv9: PGI Integration and GELAN Architecture for Enhanced Object DetectionYOLOv9 .. Advancements in Efficiency, Accuracy, and Competitiveness
- Unveiling the Mind's Canvas: Real-time Decoding of Visual Representations in the BrainExploring the Intersection of Neuroscience and AI in Understanding Brain Imaging and Perception
- Capturing Aleatoric Uncertainty: The Promise of Probabilistic Models in AIEnhancing Confidence and Decision-Making in an Uncertain World using tensorflow probability TFP
- Genetic Algorithms for Hyper-parameters TuningGenetic algorithms search for the best offspring (children) by mixing between the best parents, the best parents and children were selected by evaluation using a fitness function that we wish t
- Federated Learning for Decentralized TrainingFederated Learning enables mobile phones to collaboratively learn a shared prediction model while keeping all the training data on the device.
- An Easy Way to Add NMS to YOLOv8 graphA journey to seamlessly incorporate NMS into YOLOv8 graph, streamlining the inference process and simplifying your workflow.
- High-Resolution Image Reconstruction with Latent Diffusion Models from Human Brain ActivityReconstructing visual experiences from human brain activity with Stable Diffusion
- Evil ModelBringing Neural Network Models into Malware Attacks