13:04

Self-attention details (NLP817 11.3)

05:39

Attention recap (NLP817 11.2)

12:08

Intuition behind self-attention (NLP817 11.1)

09:27

Byte-pair encoding (BPE) (NLP817 2.6)

03:23

Stems and lemmas (NLP817 2.5)

05:30

Morphology (NLP817 2.4)

11:59

Words (NLP817 2.3)

07:41

Text normalisation and tokenisation (NLP817 2.2)

08:09

A first NLP example (NLP817 2.1)

14:53

What is natural language processing? (NLP817 1)

19:36

Edit distance (NLP817 2.7)

03:09

What should I read to learn about neural networks?

08:22

Neural networks examples: Natural language processing

06:40

Neural networks in practice

09:02

What is the difference between negative log likelihood and cross entropy? (in neural networks)

03:42

Backpropagation in general (now with forks)

13:46

Forks in neural networks

07:56

A general notation for derivatives (in neural networks)

07:18

Common derivatives for neural networks

06:56

Computational graphs and automatic differentiation for neural networks

04:03

Backprop for a multilayer feedforward neural network

31:02

Backpropagation (without forks)

03:40

Why is it called a neural network?

18:46

From logistic regression with basis functions to neural networks

06:06

Neural network preliminaries: Logistic regression, softmax and basis functions

04:12

Neural network preliminaries: Gradient descent

07:09

Neural network preliminaries: The chain rule for vector derivatives

04:38

Neural network preliminaries: Vector and matrix derivatives

01:04:25

AI, ChatGPT, and God (TGIF & KRUX 2023)

42:48

Using machine learning to assess final-year project reports (MML 2023)

22:51

Evaluating machine translation with BLEU (NLP817 10.8)

13:17

Attention - More general (NLP817 10.7)

21:30

Basic attention (NLP817 10.6)

18:12

Beam search (NLP817 10.5)

04:35

Greedy decoding (NLP817 10.4)

18:15

Encoder-decoder models in general (NLP817 10.3)

10:23

Training and loss for encoder-decoder models (NLP817 10.2)

13:08

A basic encoder-decoder model for machine translation (NLP817 10.1)

22:47

AAAI SAS 2022: Unsupervised speech segmentation (Invited Talk)

03:05

Interspeech 2021: Towards unsupervised phone & word segmentation using vector-quantized NNs

05:38

Dynamic time warping 3: Python code

17:35

Dynamic time warping 4: Aligning sequences of vectors

26:06

Dynamic time warping 2: Algorithm

12:03

Dynamic time warping 1: Motivation

22:05

Speech features intro 3: Mel-scale spectrogram

11:46

Speech features intro 4: Additional aspects

17:03

Speech features intro 2: Short-time Fourier transform

19:43

Speech features intro 1: (Fast) Fourier transform

09:55

Evaluation: Precision, recall example

18:13

Evaluation: Accuracy, precision, recall, F1

09:26

Preprocessing 2: Categorical features and categorical output

14:13

Preprocessing 1: Feature normalisation and scaling

14:48

Logistic regression 5.2: Multiclass - Softmax regression

05:16

Logistic regression 5.1: Multiclass - One-vs-rest classification

05:33

Logistic regression 4: Basis functions and regularisation

20:32

Logistic regression 3: The decision boundary and weight vector

10:46

Gradient descent 1: Fundamentals

07:15

Logistic regression 2: Optimisation

13:36

Logistic regression 1: Model and loss

07:46

Classification 4: Generative vs discriminative