Neural network architecture visualization
Adex Krost — Webinar Series

Neural Networks,
from first principles.

Architecture shapes everything. Not the tools, not the framework, not the GPU count — the architecture. These sessions examine how networks are built and why specific choices create specific outcomes.

Each session treats one concept with enough depth to be genuinely useful. No single formula fits all problems. The sessions below reflect that honestly.

Six sessions, one coherent arc

The curriculum progresses from mathematical foundations through practical implementation. Each session is self-contained but designed to build on the one before it.

01
Foundation

What a neuron actually computes

The perceptron is not a metaphor. It performs a weighted sum, applies a nonlinearity, and outputs a scalar. Starting there prevents the vague intuitions that cause confusion later.

90 min Entry level
02
Topology

Depth, width, and the capacity question

Deeper is not always better. Layer count, hidden unit count, and skip connections interact in ways that depend on dataset structure, not on theoretical guarantees.

80 min Intermediate
03
Backpropagation

Gradient flow through the computation graph

Vanishing gradients are not a mystery once you trace how partial derivatives chain through layers. Session three works through the math, then demonstrates it in NumPy without relying on autograd.

110 min Intermediate
04
Attention

Transformers: the mechanism before the hype

Scaled dot-product attention is four matrix operations. The session derives each one from the problem it was designed to solve, then builds a minimal transformer encoder from scratch.

120 min Advanced
05
Convolutional Architecture

Spatial priors and inductive bias in CNNs

Weight sharing is not a trick to reduce parameters — it is a structural assumption about the data. Session five examines ResNet-style residual paths and what motivated each design choice in 2015.

100 min Advanced
06
Applied Analysis

Reading an architecture paper without prior exposure

The final session is a live reading of a recent architecture paper. The goal is not to summarise the result but to demonstrate how to locate the architectural contribution inside dense notation.

95 min Advanced
Lecture session on neural network architecture

Instructor

Instructor portrait
Orest Valchuk
Research Lead, Adex Krost

Orest spent four years building production vision systems before moving into curriculum work. The sessions reflect his preference for derivation over demonstration.

Format note

Sessions run live with a recorded archive available within 48 hours. Participants across all time zones have equal access to materials and Q&A transcripts.

Contact us
session_03.py
def forward(x, W, b):
z = x @ W + b
# ReLU activation
return np.maximum(0, z)
def backward(dout, z, x, W):
dz = dout * (z > 0)
dW = x.T @ dz
dx = dz @ W.T
return dx, dW