12:42

Speech recognition for assessing Afrikaans and isiXhosa preschool oral narratives (ICASSP 2025)

7:21

The three types of researchers

19:14

Sampling sinusoids and exponentials

10:14

Inverse discrete-time Fourier transform

14:13

Discrete-time Fourier transform (DTFT)

16:33

LTI correlation for system identification

25:07

Overlap-and-add for fast linear filtering

5:22

LCCDE demo

12:30

FIR, IIR, LCCDE systems

7:46

Stability of LTI systems

11:08

Causality in LTI systems

5:47

LTI demo

15:16

Linear time-invariant (LTI) systems

6:57

Causality and stability in discrete systems

7:12

Linearity in discrete systems

7:37

Time-invariance in discrete systems

10:01

Introduction to discrete-time systems

5:41

Don't save money when buying sleep equipment (Surviving Life #1)

7:03

Aliasing

7:21

Discretising in time

5:42

Quantisation demo

20:38

Quantisation

7:24

Analog-to-digital conversion

6:34

Recap of the Fourier transform

13:41

Continuous convolution

7:16

Introduction to digital signal processing

59:15

Can we solve inequality in South Africa? Interview with Dieter von Fintel (TGIF 2024)

14:41

Reinforcement learning from human feedback (NLP817 12.3)

13:10

The difference between GPT and ChatGPT (NLP817 12.2)

13:56

Large language model training and inference (NLP817 12.1)

7:41

Extensions of RNNs (NLP817 9.7)

10:17

Solutions to exploding and vanishing gradients (in RNNs) (NLP817 9.6)

12:59

Vanishing and exploding gradients in RNNs (NLP817 9.5)

24:41

Backpropagation through time (NLP817 9.4)

3:22

RNN definition and computational graph (NLP817 9.3)

8:31

RNN language model loss function (NLP817 9.2)

15:04

From feedforward to recurrent neural networks (NLP817 9.1)

10:19

Embedding layers in neural networks

16:24

Git workflow extras (including merge conflicts)

23:26

A Git workflow

21:11

Evaluating word embeddings (NLP817 7.12)

11:58

GloVe word embeddings (NLP817 7.11)

15:47

Skip-gram with negative sampling (NLP817 7.10)

5:35

Continuous bag-of-words (CBOW) (NLP817 7.9)

2:30

Skip-gram example (NLP817 7.8)

9:47

Skip-gram as a neural network (NLP817 7.7)

9:49

Skip-gram optimisation (NLP817 7.6)

7:32

Skip-gram model structure (NLP817 7.5)

7:59

Skip-gram loss function (NLP817 7.4)

7:28

Skip-gram introduction (NLP817 7.3)

6:19

One-hot word embeddings (NLP817 7.2)

8:57

Why word embeddings? (NLP817 7.1)

24:00

What can large spoken language models tell us about speech? (IndabaX South Africa 2023)

4:12

Hidden Markov models in practice (NLP817 5.13)

8:33

The log-sum-exp trick (NLP817 5.12)

12:15

Why expectation maximisation works (NLP817 5.11)

20:18

Soft expectation maximisation for HMMs (NLP817 5.10)

12:06

Hard expectation maximisation for HMMs (NLP817 5.9)

8:29

Learning in HMMs (NLP817 5.8)

19:12

The forward algorithm for HMMs (NLP817 5.7)

7:11

Why do we want the marginal probability in an HMM? (NLP817 5.6)

19:16

Viterbi HMM example (NLP817 5.5)

23:50

The Viterbi algorithm for HMMs (NLP817 5.4)

2:54

The three HMM problems (NLP817 5.3)

8:35

Hidden Markov model definition (NLP817 5.2)

13:52

A first hidden Markov model example (NLP817 5.1)

14:20

What are perplexity and entropy? (NLP817 4)

2:07

Are N-gram language models still used today? (NLP817 3.12)

7:51

Kneser-Ney smoothing (NLP817 3.11)

4:28

Language model backoff (NLP817 3.10)

10:36

Language model interpolation (NLP817 3.9)

4:37

Absolute discounting in language models (NLP817 3.8)

10:26

Additive smoothing in language models (NLP817 3.7)

6:00

Language model smoothing intuition (NLP817 3.6)

8:47

Evaluating language models using perplexity (NLP817 3.5)

3:46

Why use log in language models? (NLP817 3.4)

10:47

Start and end of sentence tokens in language models (NLP817 3.3)

12:57

N-gram language models (NLP817 3.2)

10:08

The language modelling problem (NLP817 3.1)

3:35

Transformer (NLP817 11.10)

7:27

Cross-attention (NLP817 11.9)

4:43

Masking the future in self-attention (NLP817 11.8)

5:22

Multi-head attention (NLP817 11.7)

5:02

The clock analogy for positional encodings (NLP817 11.6)

19:29

Positional encodings in transformers (NLP817 11.5)

4:44

Self-attention in matrix form (NLP817 11.4)

13:04

Self-attention details (NLP817 11.3)

5:39

Attention recap (NLP817 11.2)

12:08

Intuition behind self-attention (NLP817 11.1)

9:27

Byte-pair encoding (BPE) (NLP817 2.6)

3:23

Stems and lemmas (NLP817 2.5)

5:30

Morphology (NLP817 2.4)

11:59

Words (NLP817 2.3)

7:41

Text normalisation and tokenisation (NLP817 2.2)

8:09

A first NLP example (NLP817 2.1)

14:53

What is natural language processing? (NLP817 1)

19:36

Edit distance (NLP817 2.7)

3:09

What should I read to learn about neural networks?

8:22

Neural networks examples: Natural language processing

6:40

Neural networks in practice