<?xml version="1.0" encoding="UTF-8"?>
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
<url>
<loc>https://transformers-and-math.drmhse.com</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/course-map</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/modules/01-shapes-and-linear-algebra</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/modules/02-calculus-and-optimization</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/modules/03-probability-and-information</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/modules/04-how-a-model-learns</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/modules/05-sequences-before-transformers</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/modules/06-attention</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/modules/07-the-block-and-the-full-model</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/modules/08-three-families</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/modules/09-tokenization</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/modules/10-pretraining</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/modules/11-training-across-many-gpus</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/modules/12-generation</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/modules/13-evaluation</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/modules/14-what-the-model-learns</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/modules/15-the-llama-block</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/modules/16-efficient-and-long-attention</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/modules/17-mixture-of-experts</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/modules/18-beyond-attention</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/modules/19-reading-a-model-card</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/modules/20-adaptation</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/modules/21-preference-learning</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/modules/22-reasoning-models</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/modules/23-serving</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/modules/24-quantization</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/modules/25-vision-transformers</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/modules/26-vision-language-models</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/modules/27-recognition-with-ctc</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/modules/28-generating-audio</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/modules/29-capstone</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/cardinality</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/training</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/exp</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/log</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/sum</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/subscript-index</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/d-model</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/loss</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/matrix</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/vector-space-dim</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/reals</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/element-of</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/shape</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/scalar</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/vector</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/bold-vector</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/bmatrix</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/qkv</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/matmul</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/batch</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/tensor</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/hadamard</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/d-k</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/transpose</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/rank</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/dot-product</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/norm</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/theta-params</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/token</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/one-hot</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/embedding-matrix</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/big-o</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/weights</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/dtype</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/activation</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/limit</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/to</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/approx</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/delta</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/partial</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/gradient</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/eta</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/sigma</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/mu</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/sqrt</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/expectation</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/variance</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/conditional</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/chain-rule-prob</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/maximum-likelihood</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/entropy</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/cross-entropy</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/kl-divergence</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/perplexity</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/sigmoid</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/reward</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/self-supervised</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/neuron</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/activation-function</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/mlp</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/logit</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/softmax</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/infinity</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/temperature</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/argmax</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/cases</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/kronecker</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/sqrt-dk</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/generalization</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/hyperparameter</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/chain-rule-deriv</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/product</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/alpha</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/attention</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/masking</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/concat</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/seq-len</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/residual</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/beta</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/layernorm</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/epsilon</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/ffn</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/gelu</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/forall</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/implies</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/identity-matrix</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/hat</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/lambda</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/all-reduce</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/prefill-decode</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/kv-cache</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/superscript-time</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/induction-head</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/superposition</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/rope-angle</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/set-braces</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/orthogonal</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/rmsnorm</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/d-ff</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/moe</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/floor-ceil</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/svd</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/lora</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/distillation</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/chain-of-thought</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/quantization</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/convolution</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/contrastive</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/autoencoder</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/overfitting</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/epoch</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/policy</loc>
</url>
<url>
<loc>https://transformers-and-math.drmhse.com/glossary/advantage</loc>
</url>
</urlset>
