Please note:
Behind INGOAMPT are Humans & Human can make mistakes

Day 1
Day 2
Day 3
Day 4
Day 5
Day 6
Day 7
Day 8
Day 9 _ Deep Learning, Perceptron
Day 10 _ Perceptrons types _ Regression Vs Classification
Day 11 _ Activation Function
Day 12 _ Activation Function, Hidden Layers & Non Linearity
Day 13 – What is Keras
Day 14 _ API types in Keras of Sequential, Functional and Subclassing
Day 15 _ Sequential vs Functional Keras API which is continue of day 14
Day 16 _ TensorBords, Call Backs , Model Saving in tensorflow

Day 17 _ Tuner in Keras choosing hyperparameters

Day 18 – Automatic vs Manual optimisation in Keras

Day 19 _ hyperparameter Tuning Keras

Day 20 – Vanishing Gradient

Day 21 : initialisation Weight in Deep learning

Day 22 : breakpoint in our studies : earn money by Deep learning api on MacBook

Day 23 : weight initialisation part 2

Day 24 – activation function : relu, Elu , selu , gelu , mish, etc

Day 25 : Batch Normalisation

Day 26 – Batch Normalisation – Part 2

Day 27 : Batch Normalisation trainable or non trainable batch – part 3

Day 28 : Gradient Clipping

Day 29 : Transfer Learning In Deep Learning

Day 30 – Transfer learnings part 2

Day 31 – labeled data in deep learning

Day 32 – deep learning optimisation

Day 33 – Momentum In Deep Learning

Day 34 – Momentum vs Normalistaion part 2

Day 35 – momentum part 3

Day 36 – nag in deep learning

Day 37 : AdaGrad, Origins, Mechanism and mathematical Proof

Day 38 : Adagrad , Adam

Day 39 – Adam vs SGD and other Optimisers

Day 40 – Adam optimiser

Day 41 – Adam, Nadam, AdaMax, AdamW, Etc

Day 42 – Learning Rate in Deep Learning

Day 43 – Learning Rate – Part 2

Day 44 – Learning rate – part 3

Day 45 – Learning rate – part 4

Day 46 – Keras , Tensorflow , PyTorch and MLX

Day 47 – understanding Regularization

Day 48 – DropOut

Day 49 – MaxNorm

Day 50 : optimise in deep learning summery

Day 51 : deep learning types