Fundamentals on RoboSathi

Intro to DL

Mon, 27 Apr 2026 00:00:00 +0000

PlaylistDeep Learning Fundamentals | Full Course

Deep Learning

📘 Deep learning is a subset of AI and machine learning that uses multi-layered artificial neural networks to simulate human-like learning, analyzing vast data to identify complex patterns, such as recognizing objects in photos, detecting medical anomalies, or processing natural language, like LLMs.

💡 The ‘deep’ in ‘deep learning’ stands for the idea of successive layers of representations.

XOR Problem

Mon, 27 Apr 2026 00:00:00 +0000

PlaylistDeep Learning Fundamentals | Full Course

Before we dive into the XOR problem, lets get familiar with few terms and concepts first.

Perceptron (1958)

Simplest form of an artificial neural network, acting as a single-layer binary classifier that categorizes input data into one of two groups.

It serves as a mathematical model of a biological neuron, receiving multiple signals (inputs), weighting their importance, and deciding whether to ‘fire’ (output 1) or stay ‘inactive’ (output 0).

Activation Functions

Mon, 27 Apr 2026 00:00:00 +0000

PlaylistDeep Learning Fundamentals | Full Course

Question

Why do we need activation function?

Answer

Activation Function introduces non-linearity, which allows networks to learn complex patterns in the data.

Question

Why is non-linearity important ?

Answer

Real-world data (images, speech, text, financial trends) is rarely linear. Non-linearity allows the network to learn and represent complex mappings between inputs and outputs.

It enables the network to become a ‘Universal Function Approximator’.

Universal Approximation Theorem

A neural network with following properties can approximate any continuous function.

Optimization Methods

Mon, 27 Apr 2026 00:00:00 +0000

PlaylistDeep Learning Fundamentals | Full Course

Non-Convex Loss Surface

The loss function surface in deep learning is non-convex, i.e, it has multiple local minima, saddle points, and plateaus rather than a single, global minimum.
So, in the context of neural network training, we usually do not care about finding the exact (global) minimum of a function, but seek only to reduce its value sufficiently to obtain good generalization error.