Day-18 of Machine Learning:
- Got a brief intuition on AGI (artificial general intelligence) and realised ANI (artificial narrow intelligence) had made tremendous progress and values and so on AI as compared to AGI with lots of valid reasons.
- Learnt how to implement Forward propagation using NumPy instead of TensorFlow and it gave me a basic idea about how dense function is working under the hood in TensorFlow.
- Learnt TensorFlow uses matrix to store training-set parameters in instead of vector/list for efficient computation. weight-parameters for i-th unit/neuron is arranged in i-th column of the matrix whereas row is the list of values of a parameter for units/neurons and TensorFlow utilizes a 1-D representation to store bias parameter. Also, inside dense function, matrix multiplication and sigmoid function implementation are performed.
Also,
- Practiced some basic DSA questions on LinkedList.
- Created a simplistic animation effect (gif) on python using Pillow Library, inspired by CS50P
Top comments (0)