NESTEROV ACCELERATED GRADIENT DESCENT
HOW NESTEROV GRADIENT DESCENT INCREASES EFFICIENCY OF MOMENTUM BASED DESCENTS THE PROBLEM THAT A SIMPLE MOMENTUM BASED GRADIENT DESCENT PRODUCES IS THAT IT BECAUSE OF ITS “MOMENTUM ” IT OVERSHOOTS …
MOMENTUM BASED GRADIENT DESCENT
UNDERSTANDING HOW USING “MOMENTUM ” HELPS TO MAKE LEARNING EFFICIENT IN LOW GRADIENT REGIONS AFTER LEARNING WHAT GRADIENT DESCENT MEANS , WE TRY TO ADDRESS ONE OF THE MAJOR PROBLEMS …
DEEP LEARNING IN GAMES 2
HOW TO TRAIN AN AI TO DRIVE A CAR IN GAMES LIKE NFS , GTA USING DEEP LEARNING IN GAMES (TENSORFLOW AND PYTHON) What better than an Aston Martin driving …
FINITE MARKOV DECISION PROCESS -PART 2
DESCRIBING POLICIES AND VALUE FUNCTIONS OF A MARKOV DECISION PROCESS THE LAST ARTICLE (FINITE MARKOV DECISION PROCESS -PART 1 ) WAS FOCUSED MAJORLY ON DESCRIBING WHAT WE MEAN BY RETURNS, …
FINITE MARKOV DECISION PROCESS -PART 1
DESCRIBING THE MARKOV DECISION PROCESS IN MACHINE LEARNING IN THIS POST WE DISCUSS A CERTAIN TYPE OF REINFORCEMENT PROBLEM . WE DEFINE A MERKONIKOV PROCESS AND THEN WE GET TO …
REINFORCEMENT LEARNING
THE WHAT AND HOW OF REINFORCEMENT LEARNING APART FROM SUPERVISED AND UNSUPERVISED MACHINE LEARNING , THERE IS A THIRD KIND OF MACHINE LEARNING APPROACH , WIDELY KNOWN AS REINFORCEMENT LEARNING …
K MEANS CLUSTERING IN MACHINE LEARNING
THE K MEANS CLUSTERING CLASSIFICATION ALGORITHM USED IN MACHINE LEARNING WE HAVE SEEN HOW CLASSIFICATION PROBLEMS ARE TACKLED USING LOGISTIC REGRESSIONS . HERE WE DISCUSS AN ALGORITHM THAT HELPS US …
LOGISTIC REGRESSION AND ITS ASSUMPTIONS
WHAT IS LOGISTIC REGRESSION , ITS ASSUMPTIONS AND USES IN MACHINE LEARNING ,ALGORITHMS THE WORD “REGRESSION ” IN LOGISTIC REGRESSION IS A MISNOMER . A LINEAR REGRESSION MODEL WAS SUPPOSED …
VANISHING GRADIENTS IN NEURAL NETWORKS
THE PROBLEM FACED DURING BACKPROPOGATION WHILE TRAINING NEURAL NETWORKS BACKPROPOGATION REFERS TO THE METHOD USED FOR OPTIMISING THE WEIGHTS AND BIASES OF A NEURAL NETWORK LEARNING MODEL . IT USES …
DEEP LEARNING IN GAMES
HOW WE CAN USE DEEP LEARNING IN GAMES LIKE SNAKE AND MAKE A MODEL THAT PLAYS THE GAME USING ITS “INTELLIGENCE” YOU WOULD BE SURPRISED TO KNOW THAT MANY GAMES …