---
title: "#deep-learning articles | Hashnode"
description: "Explore 2,867 articles tagged #deep-learning on Hashnode. Tutorials, guides, and how-tos from the community."
url: "https://hashnode.com/tag/deep-learning"
---

Tag

# #deep-learning

2,867 posts · 1,518 followers

[Yobitel Communications](https://hashnode.com/@yobitel) · [2h ago](https://hashnode.com/posts/how-do-growing-teams-structure-a-cvat-annotation-workflow/6b012f667508ff968ecfb935)

### [How Do Growing Teams Structure a CVAT Annotation Workflow?](https://yobitel.hashnode.dev/how-do-growing-teams-structure-a-cvat-annotation-workflow?utm_source=hashnode&utm_medium=feed)

Structure CVAT annotation workflows with smart job sizing, task assignment, quality reviews and scalable AWS deployment using Yobitel's CVAT AMI.

10 min read · [yobitel.hashnode.dev](https://yobitel.hashnode.dev/how-do-growing-teams-structure-a-cvat-annotation-workflow?utm_source=hashnode&utm_medium=feed)

[Luna Sky](https://hashnode.com/@finevoice) · [1d ago](https://hashnode.com/posts/why-ai-generated-speech-sounds-natural-in-short-clips-but-breaks-down-in-long-narration/6afecf804933132175c431c9)

### [Why AI-Generated Speech Sounds Natural in Short Clips but Breaks Down in Long Narration](https://finevoice.hashnode.dev/why-ai-generated-speech-sounds-natural-in-short-clips-but-breaks-down-in-long-narration?utm_source=hashnode&utm_medium=feed)

Why Long-Form Speech Requires More Than Consistent Voice Quality

19 min read · [finevoice.hashnode.dev](https://finevoice.hashnode.dev/why-ai-generated-speech-sounds-natural-in-short-clips-but-breaks-down-in-long-narration?utm_source=hashnode&utm_medium=feed)

[Daniel Idowu](https://hashnode.com/@idowudaniel) · [2d ago](https://hashnode.com/posts/does-an-ai-that-reads-chest-x-rays-still-work-on-x-rays-from-a-different-country-i-tested-it-with-nigerian-data/6afd79d9fa3d6846337b1370)

### [Does an AI That Reads Chest X-rays Still Work on X-rays From a Different Country? I Tested It With Nigerian Data](https://the-neural-notebook.hashnode.dev/does-an-ai-that-reads-chest-x-rays-still-work-on-x-rays-from-a-different-country-i-tested-it-with-nigerian-data?utm_source=hashnode&utm_medium=feed)

A simple write-up of an experiment I ran. This is not a research paper, and nothing here is ready for real hospitals.

10 min read · [the-neural-notebook.hashnode.dev](https://the-neural-notebook.hashnode.dev/does-an-ai-that-reads-chest-x-rays-still-work-on-x-rays-from-a-different-country-i-tested-it-with-nigerian-data?utm_source=hashnode&utm_medium=feed)

[purushothaman sinivasan](https://hashnode.com/@protechscacademy) · [2d ago](https://hashnode.com/posts/can-a-physics-informed-neural-network-replace-a-cfd-solve-we-checked-it-field-by-field-on-three-benchmarks/6afdc70efe72c8d0efd818ad)

### [Can a physics-informed neural network replace a CFD solve? We checked it field by field on three benchmarks](https://protechscacademy.hashnode.dev/can-a-physics-informed-neural-network-replace-a-cfd-solve-we-checked-it-field-by-field-on-three-benchmarks?utm_source=hashnode&utm_medium=feed)

PyTorch PINNs vs a verified finite-volume solver on Kovasznay flow, the lid-driven cavity and the Schäfer–Turek cylinder

6 min read · [protechscacademy.hashnode.dev](https://protechscacademy.hashnode.dev/can-a-physics-informed-neural-network-replace-a-cfd-solve-we-checked-it-field-by-field-on-three-benchmarks?utm_source=hashnode&utm_medium=feed)

[Logit Solutions AI](https://hashnode.com/@logitsolutionsai) · [4d ago](https://hashnode.com/posts/overfitting-visually-zero-training-errors-and-accuracy-fell-from-98-6-to-85/6afb10a05545e986507be598)

### [Overfitting, visually: zero training errors, and accuracy fell from 98.6% to 85%](https://logitsolutionsai.hashnode.dev/overfitting-visually-zero-training-errors-and-accuracy-fell-from-98-6-to-85?utm_source=hashnode&utm_medium=feed)

Deep Learning, Visually #21: a real network learns the shape, then memorizes the noise

6 min read · [logitsolutionsai.hashnode.dev](https://logitsolutionsai.hashnode.dev/overfitting-visually-zero-training-errors-and-accuracy-fell-from-98-6-to-85?utm_source=hashnode&utm_medium=feed)

[Michał Piszczek](https://hashnode.com/@michalpiszczek) · [5d ago](https://hashnode.com/posts/stored-depth-vs-executed-depth-how-to-read-a-looped-model-card/6afa2a7ef63d30664c3f80bf)

### [Stored depth vs executed depth: how to read a looped model card](https://piszczek.hashnode.dev/stored-depth-vs-executed-depth-how-to-read-a-looped-model-card?utm_source=hashnode&utm_medium=feed)

A 36-layer model can run 96 layers. Here's what that changes about the numbers you compare.

4 min read · [piszczek.hashnode.dev](https://piszczek.hashnode.dev/stored-depth-vs-executed-depth-how-to-read-a-looped-model-card?utm_source=hashnode&utm_medium=feed)

[Logit Solutions AI](https://hashnode.com/@logitsolutionsai) · [Nov 9](https://hashnode.com/posts/batch-normalization-visually-the-reset-that-keeps-deep-networks-steady/6af200bd3bb56a980ff1851a)

### [Batch normalization, visually: the reset that keeps deep networks steady](https://logitsolutionsai.hashnode.dev/batch-normalization-visually-the-reset-that-keeps-deep-networks-steady?utm_source=hashnode&utm_medium=feed)

Deep Learning, Visually #20 Watch the Short: youtube.com/shorts/yYxpjlvW69s Why the numbers drift A deep network is a chain of layers. Each layer takes a weighted sum of the activations from the layer

5 min read · [logitsolutionsai.hashnode.dev](https://logitsolutionsai.hashnode.dev/batch-normalization-visually-the-reset-that-keeps-deep-networks-steady?utm_source=hashnode&utm_medium=feed)

[Nitin Kumar K](https://hashnode.com/@nitinkk) · [Nov 9](https://hashnode.com/posts/artificial-intelligence-understanding-the-technology-transforming-our-world/6af166669a846d06d050447e)

### [Artificial Intelligence: Understanding the Technology Transforming Our World](https://nitinkk.hashnode.dev/artificial-intelligence-understanding-the-technology-transforming-our-world?utm_source=hashnode&utm_medium=feed)

A Beginner-Friendly Guide to AI, Its Technologies, Applications, and Future.

12 min read · [nitinkk.hashnode.dev](https://nitinkk.hashnode.dev/artificial-intelligence-understanding-the-technology-transforming-our-world?utm_source=hashnode&utm_medium=feed)

[Min SiThu](https://hashnode.com/@itsmeminsithu) · [Nov 8](https://hashnode.com/posts/teaching-a-computer-myanmar-handwriting-why-the-dataset-has-to-come-first/6aeff8145b3d63b19ed93c25)

### [Teaching a Computer Myanmar Handwriting: Why the Dataset Has to Come First](https://itsmeminsithu.hashnode.dev/teaching-a-computer-myanmar-handwriting-why-the-dataset-has-to-come-first?utm_source=hashnode&utm_medium=feed)

To put it simply, everyone in AI says data is the new oil — but nobody tells you what to do when there is no oil. For Myanmar handwriting, there is no clean, ready-made dataset a model can learn from.

6 min read · [itsmeminsithu.hashnode.dev](https://itsmeminsithu.hashnode.dev/teaching-a-computer-myanmar-handwriting-why-the-dataset-has-to-come-first?utm_source=hashnode&utm_medium=feed)

[Inference Engineering Academy](https://hashnode.com/@inferenceacademy) · [Nov 7](https://hashnode.com/posts/how-much-gpu-memory-do-you-need-to-serve-a-70b-model/6aeebac364fc9b5ba49982ec)

### [How much GPU memory do you need to serve a 70B model?](https://inferenceacademy.hashnode.dev/how-much-gpu-memory-do-you-need-to-serve-a-70b-model?utm_source=hashnode&utm_medium=feed)

Weights, KV cache and overhead for Llama 3.1 70B, step by step

4 min read · [inferenceacademy.hashnode.dev](https://inferenceacademy.hashnode.dev/how-much-gpu-memory-do-you-need-to-serve-a-70b-model?utm_source=hashnode&utm_medium=feed)

[2](https://hashnode.com/posts/how-much-gpu-memory-do-you-need-to-serve-a-70b-model/6aeebac364fc9b5ba49982ec)
