mhtirogla
Home
Systems
API
Pricing
About
Log in
← Back
Home
›
Systems
›
AI applications
machine-translation
machine translation
DeepL
System
Techniques · 4
Primitives · 32
machine-translation
Near-duplicate detection with MinHa…
machine-learning · medium: Estimate set Jaccard similarity from k min-hashes and find similar pairs with banded LSH buckets; the standard dedup for web crawls, training corpora and sequence collections.
›
Beam search decoding
ml-training · medium: Keep the k best partial sequences by summed log-probability at every step, set finished ones aside, and return the best (n-best) by a length-normalised score.
›
Knowledge distillation
ml-training · medium: Train a small student to match a large teacher's softened outputs (plus the hard labels) so it keeps most of the teacher's accuracy at a fraction of the cost.
›
HNSW
search-sort · medium: Hierarchical Navigable Small World: a layered proximity graph searched greedily from a sparse top layer; the default in-memory approximate nearest-neighbour index.
›
Constrained decoding
agentic-ai · low: Force LLM output to match a regex, JSON schema or grammar by masking, at every step, the tokens that would leave the language.
›
Attention variants
machine-learning · low: Multi-head, multi-query, grouped-query, sliding-window and latent attention; same softmax(QKᵀ/√d)V core, different trade-offs between quality and KV-cache size.
›
Back translation
machine-learning · low: Data augmentation for translation: translate monolingual target text back to source to make synthetic parallel pairs
Byte-pair encoding (BPE) tokenizati…
machine-learning · low: Learn a subword vocabulary by repeatedly merging the most frequent adjacent pair; byte-level BPE encodes any input losslessly with 32k-200k tokens.
›
Embeddings
machine-learning · low: A learned table mapping discrete ids to dense vectors: gather forward, sparse scatter-add backward, row-wise optimizers to keep huge tables cheap.
›
Evaluation metrics
machine-learning · low: Precision, recall, ROC AUC, average precision, log loss, NDCG and pass@k computed correctly, plus paired confidence intervals for comparing models.
›
Language identification
machine-learning · low: Score a text's character n-grams against per-language statistics, after a cheap script check, and return an ISO 639 code with a confidence or "und".
›
Regularization
machine-learning · low: Techniques that trade training fit for generalization: weight decay, dropout, early stopping, label smoothing and data mixing, with the exact update rules and defaults.
›
Text normalization
machine-learning · low: Rewrite messy text into one canonical form for matchers and models, or into spoken words for speech output (and back), keeping a map to the original offsets.
›
Continuous batching
ml-training · low: Schedule LLM inference per iteration, not per request; finished sequences leave and new ones join the running batch every step, which keeps the GPU full.
›
Transformer block
ml-training · low: The decoder-only pre-norm block (attention plus MLP on a residual stream) behind every modern LLM, with exact shapes, parameter, FLOP and KV-cache counts.
›
Weight quantization
ml-training · low: Store weights as 8/4-bit integers with per-group scales; decode is memory-bound, so 4-bit weights give about 3-4x tokens/s and fit 4x larger models.
›
Fast hash functions
data-structures · low: Non-cryptographic hashes built from 64×64→128-bit multiplies and xor-shifts; pick by key size, trust level and whether the hash is persisted.
›
Rolling hash
data-structures · low: Rabin-Karp polynomial rolling hashes and winnowing for substring fingerprints and document matching
Swiss table
data-structures · low: Open-addressing hash table that filters 8-16 slots at once with 1-byte hash tags and SIMD, giving fast lookups at 87.5 % load.
›
d-ary heap
data-structures · low: Array heap with d children per node (d = 4 typical): half the binary heap's depth, siblings in one cache line, faster priority queues.
›
+ 16 more primitives
System
Techniques · 4
Primitives · 32
machine-translation
Near-duplicate detection with MinHa…
machine-learning · medium: Estimate set Jaccard similarity from k min-hashes and find similar pairs with banded LSH buckets; the standard dedup for web crawls, training corpora and sequence collections.
›
Beam search decoding
ml-training · medium: Keep the k best partial sequences by summed log-probability at every step, set finished ones aside, and return the best (n-best) by a length-normalised score.
›
Knowledge distillation
ml-training · medium: Train a small student to match a large teacher's softened outputs (plus the hard labels) so it keeps most of the teacher's accuracy at a fraction of the cost.
›
HNSW
search-sort · medium: Hierarchical Navigable Small World: a layered proximity graph searched greedily from a sparse top layer; the default in-memory approximate nearest-neighbour index.
›
Constrained decoding
agentic-ai · low: Force LLM output to match a regex, JSON schema or grammar by masking, at every step, the tokens that would leave the language.
›
Attention variants
machine-learning · low: Multi-head, multi-query, grouped-query, sliding-window and latent attention; same softmax(QKᵀ/√d)V core, different trade-offs between quality and KV-cache size.
›
Back translation
machine-learning · low: Data augmentation for translation: translate monolingual target text back to source to make synthetic parallel pairs
Byte-pair encoding (BPE) tokenizati…
machine-learning · low: Learn a subword vocabulary by repeatedly merging the most frequent adjacent pair; byte-level BPE encodes any input losslessly with 32k-200k tokens.
›
Embeddings
machine-learning · low: A learned table mapping discrete ids to dense vectors: gather forward, sparse scatter-add backward, row-wise optimizers to keep huge tables cheap.
›
Evaluation metrics
machine-learning · low: Precision, recall, ROC AUC, average precision, log loss, NDCG and pass@k computed correctly, plus paired confidence intervals for comparing models.
›
Language identification
machine-learning · low: Score a text's character n-grams against per-language statistics, after a cheap script check, and return an ISO 639 code with a confidence or "und".
›
Regularization
machine-learning · low: Techniques that trade training fit for generalization: weight decay, dropout, early stopping, label smoothing and data mixing, with the exact update rules and defaults.
›
Text normalization
machine-learning · low: Rewrite messy text into one canonical form for matchers and models, or into spoken words for speech output (and back), keeping a map to the original offsets.
›
Continuous batching
ml-training · low: Schedule LLM inference per iteration, not per request; finished sequences leave and new ones join the running batch every step, which keeps the GPU full.
›
Transformer block
ml-training · low: The decoder-only pre-norm block (attention plus MLP on a residual stream) behind every modern LLM, with exact shapes, parameter, FLOP and KV-cache counts.
›
Weight quantization
ml-training · low: Store weights as 8/4-bit integers with per-group scales; decode is memory-bound, so 4-bit weights give about 3-4x tokens/s and fit 4x larger models.
›
Fast hash functions
data-structures · low: Non-cryptographic hashes built from 64×64→128-bit multiplies and xor-shifts; pick by key size, trust level and whether the hash is persisted.
›
Rolling hash
data-structures · low: Rabin-Karp polynomial rolling hashes and winnowing for substring fingerprints and document matching
Swiss table
data-structures · low: Open-addressing hash table that filters 8-16 slots at once with 1-byte hash tags and SIMD, giving fast lookups at 87.5 % load.
›
d-ary heap
data-structures · low: Array heap with d children per node (d = 4 typical): half the binary heap's depth, siblings in one cache line, faster priority queues.
›
Top-k selection
search-sort · low: Keep the k best of n items without sorting all n - bounded min-heap for streams, quickselect for arrays, threshold pruning to skip most items.
›
Data augmentation
machine-learning · low: Generate label-preserving variants of each training example on the fly to enlarge the effective dataset and bake in invariances.
›
Loss functions
machine-learning · low: The scalar a model minimizes: cross-entropy for classes and tokens, MSE or Huber for values, each with a stable form and simple gradient.
›
Token sampling
ml-training · low: Turn a vector of scores into one chosen item with temperature, top-k, top-p, min-p, repetition penalties and a seed.
›
SIMD programming
hardware-os · low: Process 4-16 lanes per instruction with AVX2, AVX-512 or NEON via Rust std::arch, with runtime dispatch and a portable fallback.
›
PRNGs (PCG, xoshiro)
numerics · low: Small, fast, statistically strong non-cryptographic generators: PCG32 and xoshiro256**, with seeding, parallel streams and unbiased ranges.
›
Scalar quantization
search-sort · low: Per-dimension int8/binary quantization of vectors with rescoring
Reference counting
compilers · low: Keep a count of owners in each object, free it when the count hits zero; deterministic and local, but pays on every copy and leaks cycles.
›
AdamW
ml-training · low: Adam's per-parameter adaptive steps with weight decay applied directly to the weights; the default optimizer for transformers and LLM pretraining.
›
Paged KV cache
ml-training · low: Store each sequence's attention keys/values in fixed-size blocks mapped through a block table, like virtual memory pages; near-zero fragmentation and copy-on-write sharing.
›
Reverse-mode automatic differentiat…
ml-training · low: Record the forward computation on a tape, then sweep it backwards once to get the gradient of a scalar loss for all inputs.
›
Low precision number formats
numerics · low: Bf16, fp16, fp8 (E4M3, E5M2), MX block formats and int4: ranges, rounding, scaling
LU and Cholesky factorization
numerics · low: Factor A = PLU (any square matrix, partial pivoting) or A = LLᵀ (SPD) once in O(n³), then solve each right-hand side in O(n²).
›
Finite state transducer
search-sort · low: Minimal acyclic FST mapping sorted keys to values; compact term dictionaries with prefix/fuzzy search
JSON Schema validation
security · low: Compile a JSON Schema once, then check every untrusted document against it, within hard size and depth limits, and report failures as JSON Pointers.
›
Bootstrap confidence intervals
statistics · low: Resampling-based confidence intervals for arbitrary statistics
Copy for AI
Similar systems
Share the most building blocks with this one.
prompt-injection-detection
29 %
abuse-classifier
24 %
synthetic-data
22 %
embedding-service
21 %
mobile-keyboard-ime
20 %