https://insideaimodels.com Practical deep learning, explained. Tutorials, experiments, and the details papers leave out — free, for anyone learning AI. en https://insideaimodels.com/blog/hello-world https://insideaimodels.com/blog/hello-world Fri, 26 Jun 2026 00:00:00 GMT A short introduction to why I started this journal, the kinds of posts you'll find here, and why writing is an inseparable part of learning. Meta https://insideaimodels.com/blog/what-is-a-tensor https://insideaimodels.com/blog/what-is-a-tensor Wed, 24 Jun 2026 00:00:00 GMT We build the ladder from scalars to tensors, make the case that shape is the concept to track, and show why a neural network layer is really just linear algebra in disguise. Linear AlgebraFundamentals https://insideaimodels.com/blog/attention-explained https://insideaimodels.com/blog/attention-explained Tue, 23 Jun 2026 00:00:00 GMT We build the mechanism at the heart of modern language models around a single intuitive question, working from query, key, and value vectors through softmax to why attention changed everything. TransformersDeep Learning https://insideaimodels.com/blog/how-gradient-descent-works https://insideaimodels.com/blog/how-gradient-descent-works Mon, 22 Jun 2026 00:00:00 GMT The optimization loop behind every trained model, built from a hill-and-fog analogy through derivatives, learning rate, and backpropagation — no calculus prerequisite required. FundamentalsDeep Learning https://insideaimodels.com/blog/identity-aware-negatives https://insideaimodels.com/blog/identity-aware-negatives Sat, 20 Jun 2026 00:00:00 GMT In multimodal deepfake detection, a contrastive loss is only as good as its negatives. We examine why random batching misses the critical negatives and how identity-grouped sampling repairs it. Deep LearningResearch