Skip to content
Deep Learning
Deep Learning syllabus
DL Syllabus
Deep Learning syllabus
1
What is TensorFlow keras
2
Introduction to neural networks
3
Multi-layer perceptron: first example of a network
4
Activation functions
5
Backpropagation
6
Regularization methods
7
Simple linear regression using TensorFlow Keras
8
Logistic regression on the MNIST dataset using TensorFlow Keras
9
ConvNets in TensorFlow: The math behind CNN
10
Other CNN architectures
11
Recognizing CIFAR-10 images with deep learning
12
Word embedding fundamentals (Word2Vec and GloVe)
13
Word2Vec models: CBOW and Skip-gram arthitectures
14
Creating custom Azerbaijani embeddings using Gensim
15
Language model-based embeddings: BERT, ULMFiT, GPT
16
How Recurrent Neural Networks works?
17
Long short-term memory (LSTM)
18
Gated recurrent unit (GRU)
19
RNN variants
20
Text cleaning
21
Use case: Azerbaijani novel generation using Recurrent Neural Networks
22
Encoder-decoder architecture – seq2seq
23
Attention mechanism
24
Use case: Building seq2seq network with/without attention mechanism for machine translation (Az - Eng)
25
Transformers: Understanding architecture
26
Language models: BERT, Reformer, GPT-2,3, RoBERTa, ELECTRA and etc.
27
Using Hugging Face models
28
Introduction to Generative Adversarial Networks
29
DCGAN for MNIST digits
30
Flow-based models for data generation
31
Diffusion models for data generation
32
Introduction to Docker, Flask, FastAPI
33
Deploying Deep Learning Model in Heroku using flask
There are no rows in this table
Want to print your doc?
This is not the way.
This is not the way.
Try clicking the ⋯ next to your doc name or using a keyboard shortcut (
CtrlP
) instead.