Formal & Physical Sciences AI — Models & ResearchENGenerative AI L16: LSTMsAgha Ali RazaMarch 11, 2026 35 min★ ★ ★ ★ ☆ 4/5LSTMRecurrent Neural NetworksDeep Learning
Formal & Physical Sciences AI — Models & ResearchEN[Generative AI in Urdu/Hindi] Lecture 18: Positional encodingsAgha Ali RazaMarch 8, 2026 53 min★ ★ ★ ★ ☆ 4/5TransformerPositional EncodingDeep Learning
Formal & Physical Sciences AI — Models & ResearchEN[Generative AI in Urdu/Hindi] Lecture 17: Transformers (first pass)Agha Ali RazaMarch 6, 2026 54 min★ ★ ★ ★ ☆ 4/5TransformerSelf-AttentionMulti-Head Attention
Formal & Physical Sciences AI — Models & ResearchEN[Generative AI in Urdu/Hindi] Lecture 16: attention, drawbacks of RNN & LSTM, intro. to transformersAgha Ali RazaMarch 1, 2026 58 min★ ★ ★ ★ ☆ 4/5AttentionTransformersRNN
Formal & Physical Sciences AI — Models & ResearchEN[Generative AI in Urdu/Hindi] Lecture 15: Methods of computing attentionAgha Ali RazaFebruary 27, 2026 24 min★ ★ ★ ★ ☆ 4/5Attention MechanismsSequence-to-SequenceDeep Learning
Formal & Physical Sciences AI — Models & ResearchENGenerative AI in Urdu/Hindi Lecture 14: Conditional language models, encoder-decoder, attention.Agha Ali RazaFebruary 22, 2026 58 min★ ★ ★ ★ ☆ 4/5AttentionEncoder-DecoderMachine Translation
Formal & Physical Sciences AI — Models & ResearchENGenerative AI in Urdu/Hindi Lecture 13: LSTMs, bi-directional, multi-layer, teacher forcing.Agha Ali RazaFebruary 20, 2026 58 min★ ★ ★ ★ ☆ 4/5LSTMRNNDeep Learning
Formal & Physical Sciences AI — Models & ResearchEN[Generative AI in Urdu/Hindi] Lecture 12: RNN variations, its issues, possible solutions. LSTMs.Agha Ali RazaFebruary 15, 2026 57 min★ ★ ★ ★ ☆ 4/5RNNLSTMGradient Vanishing
Formal & Physical Sciences AI — Models & ResearchEN[Generative AI in Urdu/Hindi] Lecture 11: RNNs training, derivations, applications and more!Agha Ali RazaFebruary 13, 2026 73 min★ ★ ★ ★ ☆ 4/5RNNBackpropagation Through TimeDeep Learning
Formal & Physical Sciences AI — Models & ResearchEN[Generative AI in Urdu/Hindi] Lecture 10: Feed-forward NNs, pooling layer, sequence modelling, RNNsAgha Ali RazaFebruary 8, 2026 48 min★ ★ ★ ★ ☆ 4/5RNNCBoWSequence Modeling
Formal & Physical Sciences AI — Models & ResearchENGenerative AI in Urdu/Hindi Lecture 9: Developing a complete feed-forward neural networkAgha Ali RazaFebruary 6, 2026 75 min★ ★ ★ ★ ☆ 4/5Neural NetworksBackpropagationGradient Descent
Formal & Physical Sciences AI — Models & ResearchEN[Generative AI in Urdu/Hindi] Lecture 8: Embeddings: maths, negative sampling, best practices, biasAgha Ali RazaFebruary 1, 2026 74 min★ ★ ★ ★ ☆ 4/5Word EmbeddingsSkip-GramNegative Sampling
Formal & Physical Sciences AI — Models & ResearchEN[Generative AI in Urdu/Hindi] Lecture 7: Embeddings (cont.) - Word2vec, Skipgram, CBOWAgha Ali RazaJanuary 30, 2026 77 min★ ★ ★ ★ ☆ 4/5Word2vecEmbeddingsNLP
Formal & Physical Sciences AI — Models & ResearchEN[Generative AI in Urdu/Hindi] Lecture 6: Embeddings – Word formations, ambiguity, vectorizationAgha Ali RazaJanuary 25, 2026 78 min★ ★ ★ ★ ☆ 4/5EmbeddingsNLPWord Semantics
Formal & Physical Sciences AI — Models & ResearchEN[Generative AI in Urdu/Hindi] Lecture 5: Tokenization (cont.) – algorithms, examples, best practicesAgha Ali RazaJanuary 23, 2026 52 min★ ★ ★ ★ ☆ 4/5TokenizationBPEWordPiece
Formal & Physical Sciences AI — Models & ResearchEN[Generative AI in Urdu/Hindi] Lecture 4: Tokenization – concept, types, their problems, solutionsAgha Ali RazaJanuary 18, 2026 77 min★ ★ ★ ★ ☆ 4/5TokenizationNLPLLM
Formal & Physical Sciences AI — Models & ResearchEN[Generative AI in Urdu/Hindi] Lecture 3: Language - embeddings to encoding, modelling to fine-tuningAgha Ali RazaJanuary 16, 2026 81 min★ ★ ★ ★ ☆ 4/5Generative AILanguage ModelsEmbeddings
Formal & Physical Sciences AI — Models & ResearchENGenerative AI in Urdu/Hindi] Lecture 2: Language – concepts to terminologies, vectors to embeddingsAgha Ali RazaJanuary 11, 2026 77 min★ ★ ★ ★ ☆ 4/5NLPLinguisticsTokenization
Formal & Physical Sciences AI — Models & ResearchENGenerative AI in Urdu/Hindi Lecture 1: Course expectations, objectives and contentsAgha Ali RazaJanuary 9, 2026 20 min★ ★ ★ ★ ☆ 4/5Generative AINLPCourse Introduction
![[Generative AI in Urdu/Hindi] Lecture 18: Positional encodings](https://i.ytimg.com/vi/5ElJUeInD5g/maxresdefault.jpg)
![[Generative AI in Urdu/Hindi] Lecture 17: Transformers (first pass)](https://i.ytimg.com/vi/-FEuUtT_T_E/maxresdefault.jpg)
![[Generative AI in Urdu/Hindi] Lecture 16: attention, drawbacks of RNN & LSTM, intro. to transformers](https://i.ytimg.com/vi/5Z11FbrWswk/maxresdefault.jpg)
![[Generative AI in Urdu/Hindi] Lecture 15: Methods of computing attention](https://i.ytimg.com/vi/s82WGvA8MMg/maxresdefault.jpg)
![[Generative AI in Urdu/Hindi] Lecture 12: RNN variations, its issues, possible solutions. LSTMs.](https://i.ytimg.com/vi/aQRcM6g_mJw/maxresdefault.jpg)
![[Generative AI in Urdu/Hindi] Lecture 11: RNNs training, derivations, applications and more!](https://i.ytimg.com/vi/xvFnn_dDJK0/maxresdefault.jpg)
![[Generative AI in Urdu/Hindi] Lecture 10: Feed-forward NNs, pooling layer, sequence modelling, RNNs](https://i.ytimg.com/vi/INcVmFLzpU4/maxresdefault.jpg)
![[Generative AI in Urdu/Hindi] Lecture 8: Embeddings: maths, negative sampling, best practices, bias](https://i.ytimg.com/vi/KVb15f8RWjI/maxresdefault.jpg)
![[Generative AI in Urdu/Hindi] Lecture 7: Embeddings (cont.) - Word2vec, Skipgram, CBOW](https://i.ytimg.com/vi/NNHDsSmJbic/maxresdefault.jpg)
![[Generative AI in Urdu/Hindi] Lecture 6: Embeddings – Word formations, ambiguity, vectorization](https://i.ytimg.com/vi/lQUgj8t1lsc/maxresdefault.jpg)
![[Generative AI in Urdu/Hindi] Lecture 5: Tokenization (cont.) – algorithms, examples, best practices](https://i.ytimg.com/vi/pRBDh1zj9nQ/maxresdefault.jpg)
![[Generative AI in Urdu/Hindi] Lecture 4: Tokenization – concept, types, their problems, solutions](https://i.ytimg.com/vi/VYGzh23q7n4/maxresdefault.jpg)
![[Generative AI in Urdu/Hindi] Lecture 3: Language - embeddings to encoding, modelling to fine-tuning](https://i.ytimg.com/vi/IUGf8e3uEfo/maxresdefault.jpg)
![Generative AI in Urdu/Hindi] Lecture 2: Language – concepts to terminologies, vectors to embeddings](https://i.ytimg.com/vi/RkqRDK7h7po/maxresdefault.jpg)
