ingoampt July 26, 2024 80 Days of AI Mastery: Learn Deep Learning Day by Day Machine learning (ML) Overview _ Day 1 Day 1 integrate ML into iOS Apps _ Day 2 Day 2 Models based, Instance Models, Train-Test Splits: The Building Blocks of Machine Learning Explained – Day 3 Day 3 Regression & Classification with MNIST. _ day 4 Day 4 Mathematical Explanation behind SGD Algorithm in Machine Learning _ day 5 Day 5 Can we make prediction without need of going through iteration ? yes with the Normal Equation _ Day 6 Day 6 What is Gradient Decent in Machine Learning? _ Day 7 Day 7 3 Types of Gradient Decent Types : Batch, Stochastic & Mini-Batch _ Day 8 Day 8 Deep Learning _ Perceptrons – day 9 Day 9 Regression vs Classification Multi Layer Perceptrons (MLPs) _ day 10 Day 10 Activation Function _ day 11 Day 11 Activation Function, Hidden Layer and non linearity. _ day 12 Day 12 What is Keras _ day 13 Day 13 sequential , functional and model subclassing API in Keras _ day 14 Day 14 Sequential vs Functional Keras API Part 2 explanation _ Day 15 Day 15 TensorFlow: Using TensorBoard, Callbacks, and Model Saving in Keras _. day 16 Day 16 Hyperparameter Tuning with Keras Tuner _ Day 17 Day 17 Automatic vs Manual optimisation in Keras_. day 18 Day 18 Mastering Hyperparameter Tuning & Neural Network Architectures: Exploring Bayesian Optimization_ Day 19 Day 19 Vanishing gradient explained in detail _ Day 20 Day 20 Weight initialisation in Deep Learning well explained _ Day 21 Day 21 How Create API by Deep Learning to Earn Money and what is the Best Way for Mac Users – Breaking studies on Day 22 Day 22 Weight initialazation part 2 – day 23 Day 23 Activation function progress in deep learning, Relu, Elu, Selu, Geli , mish, etc – include table and graphs – day 24 Day 24 Batch Normalization – day 25 Day 25 Batch normalisation part 2 – day 26 Day 26 Batch normalisation – trainable and non trainable – day 27 Day 27 Understanding Gradient Clipping in Deep Learning – day 28 Day 28 Transfer learning – day 29 Day 29 How do Transfer Learning in Deep Learning Model – with an example – Day 30 Day 30 Fundamentals of labeled vs unlabeled data in Machine Learning – Day 31 Day 31 Mastering Deep Neural Network Optimization: Techniques and Algorithms for Faster Training – Day 32 Day 32 Momentum Optimization in Machine Learning: A Detailed Mathematical Analysis and Practical Application – Day 33 Day 33 Momentum vs Normalization in Deep learning -Part 2 – Day 34 Day 34 Momentum – part 3 – day 35 Day 35 Nag as optimiser in deep learning – day 36 Day 36 A Comprehensive Guide to AdaGrad: Origins, Mechanism, and Mathematical Proof – Day 37 Day 37 AdaGrad vs RMSProp vs Adam: Why Adam is the Most Popular? – Day 38 Day 38 Adam vs SGD vs AdaGrad vs RMSprop vs AdamW – Day 39 Day 39 Adam Optimizer deeply explained by Understanding Local Minimum – Day 40 Day 40 Deep Learning Optimizers: NAdam, AdaMax, AdamW, and NAG Comparison – Day 41 Day 41 The Power of Learning Rates in Deep Learning and Why Schedules Matter – Day 42 Day 42 Theory Behind 1Cycle Learning Rate Scheduling & Learning Rate Schedules – Day 43 Day 43 Exploring Gradient Clipping & Weight Initialization in Deep Learning – Day 44 Day 44 Learning Rate – 1-Cycle Scheduling, exponential decay and Cyclic Exponential Decay (CED) – Part 4 – Day 45 Day 45 Comparing TensorFlow (Keras), PyTorch, & MLX – Day 46 Day 46 Understanding Regularization in Deep Learning – Day 47 Day 47 DropOut and Monte Carlo Dropout (MC Dropout)- Day 48 Day 48 Learn Max-Norm Regularization to avoid overfitting : Theory and Importance in Deep Learning and proof – Day 49 Day 49 Deep Neural Networks vs Dense Network – Day 50 Day 50 Deep Learning Examples, Short OverView – Day 51 Day 51 Deep Learning Models integration for iOS Apps – briefly explained – Day 52 Day 52 CNN – Convolutional Neural Networks explained by INGOAMPT – DAY 53 Day 53 Mastering the Mathematics Behind CNN or Convolutional Neural Networks in Deep Learning – Day 54 Day 54 RNN Deep Learning – Part 1 – Day 55 Day 55 Understanding Recurrent Neural Networks (RNNs) – part 2 – Day 56 Day 56 Time Series Forecasting with Recurrent Neural Networks (RNNs) – part 3 – day 57 Day 57 Understanding RNNs: Why Not compare it with FNN to Understand the Math Behind it Better? – DAY 58 Day 58 To learn what is RNN (Recurrent Neural Networks ) why not understand ARIMA, SARIMA first ? – RNN Learning – Part 5 – day 59 Day 59 Step-by-Step Explanation of RNN for Time Series Forecasting – part 6 – day 60 Day 60 Iterative Forecasting which is Predicting One Step at a Time 2- Direct Multi-Step Forecasting with RNN 3- Seq2Seq Models for Time Series Forecasting – day 61 Day 61 UNLOCKING RNN, Layer Normalization, and LSTMs – Mastering the Depth of RNNs in Deep Learning – Part 8 of RNN Series by INGOAMPT – Day 62 Day 62 Natural Language Processing (NLP) and RNN – day 63 Day 63 Why transformers are better for NLP ? Let’s see the math behind it – Day 64 Day 64 The Transformer Model Revolution from GPT to DeepSeek & goes on How They’re Radically Changing the Future of AI – Day 65 Day 65 Transformers in Deep Learning: Breakthroughs from ChatGPT to DeepSeek – Day 66 Day 66 Do you want to read a summery of what is BERT in 2 min read? (Bidirectional Encoder Representations from Transformers) – day 67 Day 67 Brief OverView of How ChatGPT Works? – Day 68 Day 68 Can ChatGPT Truly Understand What We’re Saying? A Powerful Comparison with BERT” – Day 69 Day 69 How ChatGPT Work Step by Step – day 70 Day 70 Mastering NLP: Unlocking the Math Behind It for Breakthrough Insights with a scientific paper study – day 71 Day 71 The Rise of Transformers in Vision and Multimodal Models – Hugging Face – day 72 Day 72 Unlock the Secrets of Autoencoders, GANs, and Diffusion Models – Why You Must Know Them? -Day 73 Day 73 Understanding Unsupervised Pretraining Using Stacked Autoencoders – Day 74 Day 74 Breaking Down Diffusion Models in Deep Learning – Day 75 Day 75 Generative Adversarial Network (GANs) Deep Learning – Day 76 Day 76 How Dalle Image Generator works ? – Day 77 Day 77 Reinforcement Learning: An Evolution from Games to Real-World Impact – Day 78 Day 78 DeepNet – What Happens by Scaling Transformers to 1,000 Layers ? – Day 79 Day 79 Lets go through Paper of DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning – Day 80 Day 80
