• DAY 30: SIMCLR - SELF-SUPERVISED LEARNING PART 2 AND CLASSIFIER TRAINING
  Nov 30

• DAY 29: EXPLORING SIMCLR FOR SELF-SUPERVISED LEARNING - PART 1
  Nov 29

• DAY 28: FINE-TUNING THE BERT MODEL FOR SENTIMENT ANALYSIS
  Nov 28

• DAY 27: BUILDING A TRANSFORMER-BASED MODEL (BERT) FOR TEXT CLASSIFICATION ON IMDB DATASET
  Nov 27

• DAY 26: TRAINING THE CYCLEGAN FOR STYLE TRANSFER - PART 2: HORSE TO ZEBRA CONVERSION
  Nov 26

• DAY 25: EXPLORING CYCLEGAN FOR STYLE TRANSFER - PART 1: MODEL ARCHITECTURE AND SETUP
  Nov 25

• DAY 24: EXPLORING CONDITIONAL GANS (CGANS) WITH FASHION MNIST
  Nov 24

• DAY 23: GAN IMPROVEMENTS - ENHANCING PERFORMANCE FOR FASHION MNIST GENERATION
  Nov 23

• DAY 22: GAN BASICS - UNDERSTANDING GAN ARCHITECTURE AND SETTING UP A GAN FRAMEWORK
  Nov 22

• DAY 21: FINE-TUNE AND EVALUATE AUTOENCODER MODEL FOR ANOMALY DETECTION
  Nov 21

• DAY 20: BUILDING AN AUTOENCODER-BASED ANOMALY DETECTION SYSTEM (PART 1: DATA AND MODEL SETUP)
  Nov 20

• DAY 19: ATTENTION MECHANISM FOR LSTM IN MACHINE TRANSLATION
  Nov 18

• DAY 18: UNDERSTANDING ATTENTION MECHANISM FOR LSTM IN MACHINE TRANSLATION
  Nov 18

• DAY 17: BUILDING AN LSTM MODEL FOR SENTIMENT ANALYSIS
  Nov 17

• DAY 16: BUILDING AND TRAINING THE RNN MODEL FOR TEMPERATURE FORECASTING
  Nov 16

• DAY 15: PREPARING TIME SERIES DATA FOR TEMPERATURE FORECASTING
  Nov 15

• DAY 14: BUILDING A CUSTOM CNN-BASED STUDENT MODEL USING A PRE-TRAINED TEACHER MODEL
  Nov 14

• DAY 13: EXPLORE IMAGE SEGMENTATION WITH U-NET ON CARVANA DATASET
  Nov 13

• DAY 12: IMPLEMENTING YOLO FOR OBJECT DETECTION
  Nov 12

• DAY 11: APPLY TRANSFER LEARNING WITH VGG16 FOR A SIMPLE CLASSIFICATION TASK
  Nov 11

• DAY 10: DATA AUGMENTATION WITH FASHION MNIST
  Nov 10

• DAY 9: MODIFY CNN WITH POOLING LAYERS AND VISUALIZE FILTERS
  Nov 9

• DAY 8: BUILD A SIMPLE CNN FOR CIFAR-10 IMAGE CLASSIFICATION
  Nov 8

• DAY 7: FINE-TUNE HYPERPARAMETERS WITH KERAS TUNER ON A SMALL NN
  Nov 7

• DAY 6: APPLY DROPOUT AND REGULARIZATION (L2) FOR OVERFITTING CONTROL (TITANIC DATASET)
  Nov 6

• DAY 5: EXPERIMENT WITH OPTIMIZERS (SGD, ADAM, RMSPROP) USING A PRE-BUILT CNN ON CIFAR-10
  Nov 5

• DAY 4: COMPARE ACTIVATION FUNCTIONS (RELU, SIGMOID, TANH) ON FASHION MNIST
  Nov 4

• DAY 3: EXPLORE BACKPROPAGATION THEORY AND TWEAK LEARNING RATES (MNIST)
  Nov 3

• DAY 2: CLASSIFY HANDWRITTEN DIGITS USING A SIMPLE NN ON MNIST
  Nov 2

• DAY 1: PREDICT HOUSE PRICES USING A FEEDFORWARD NEURAL NETWORK (NN)
  Nov 1