LibreTimes

Search results for “BERT”

Categories

35 results

Machine Learning 2. Lecture 4. Attention Models and Transformers

2026LectureКонстантин Вячеславович Воронцов

Sequence-to-sequence problems: the recurrent network, the encoder–decoder architecture and its limitations; the recurrent network with an attention model, interpreting the attention matrix in machine translation and image captioning; similarity functions, the query–key–value attention model, the attention formula, self-attention; multi-head attention and its regularisation, hierarchical attention for document classification, the graph attention model GAT; the transformer for machine translation: the encoder, positional encoding, layer normalisation and skip connections, the decoder with masking, the training criterion, BLEU and WER; the transformer encoder BERT, the MLM and NSP criteria, fine-tuning, BPE and WordPiece tokenisation, model sizes.
1
450

The torsion component of the Picard scheme

2026OtherBogdan Zavyalov

Every finite flat commutative group scheme over a noetherian local ring is the torsion component of the Picard scheme of a smooth projective scheme with 3-dimensional fibers, built as a quotient of a complete intersection. An application: Hodge numbers that jump in a smooth projective family.
1
500

Some examples of algebraic groups

2026TheorySean Cotner

Two pathological phenomena for algebraic groups over general bases — a group degenerating between the multiplicative and additive group across a DVR, and a non-affine identity component — built as centralizers in SL_n.

0
180

Systems of Linear Equations

2026TheorySergey

Linear systems in matrix form, the Kronecker–Capelli theorem, homogeneous systems, and the fundamental system of solutions.
0
210

Quadratic Forms

2026TheorySergey

Quadratic forms and their matrix, definiteness, Sylvester's criterion, and canonical form.
0
160

IMO 1965

2026Problem sheet

International mathematics competition for pre-university students, held annually since 1959. Six problems over two days.
0
320

IMO 1966

2026Problem sheet

International mathematics competition for pre-university students, held annually since 1959. Six problems over two days.
0
190

IMO 1984

2026Problem sheet

International mathematics competition for pre-university students, held annually since 1959. Six problems over two days.
0
150

IMO 1990

2026Problem sheet

International mathematics competition for pre-university students, held annually since 1959. Six problems over two days.
0
220

IMO 1996

2026Problem sheet

International mathematics competition for pre-university students, held annually since 1959. Six problems over two days.
0
270

IMO 1997

2026Problem sheet

International mathematics competition for pre-university students, held annually since 1959. Six problems over two days.
0
200

IMO 2003

2026Problem sheet

International mathematics competition for pre-university students, held annually since 1959. Six problems over two days.
0
190

IMO 2016

2026Problem sheet

57th International Mathematical Olympiad. Hong Kong, 2016.
0
440

IMO 2019

2026Problem sheet

60th International Mathematical Olympiad, 2019.
0
390

Algebra 1. Seminar 2

2026Problem sheetАртём Авилов

Problems for seminar 2 of the course "Algebra 1" (A. A. Avilov, Independent University of Moscow, autumn 2026), 14 September 2026 — group homomorphisms, the homomorphism theorem, conjugate elements, group actions. The group Hom⁡(A,B)\operatorname{Hom}(A, B) of abelian groups; multiplicativity of the index; the third isomorphism theorem; isomorphic subgroups with non-isomorphic quotients; conjugacy in SnS_n and cycle type; conjugacy classes of A5A_5; Aut⁡(Sn)=Sn\operatorname{Aut}(S_n) = S_n for n≠6n \ne 6; the rotation and symmetry groups of the cube; a homomorphism S4→S3S_4 \to S_3; the symmetry group of the icosahedron; the automorphism group of the Petersen graph.

0
180

Properties of Matrix Operations

2026TheorySergey

The basic properties of addition, scalar multiplication, transposition, and multiplication of matrices, with justifications.
0
180

Determinant via Permutations

2026TheorySergey

The direct definition of a determinant via permutations: inversions, parity, and a sum of n! terms.

0
170

Basis, Dimension, and Span

2026TheorySergey

Linear dependence of vectors, basis and coordinates, dimension, subspaces, and linear span.
0
220