Mariusz Bojarski

Learn More
We trained a convolutional neural network (CNN) to map raw pixels from a single front-facing camera directly to steering commands. This end-to-end approach proved surprisingly powerful. With minimum training data from humans the system learns to drive in traffic on local roads with or without lane markings and on highways. It also operates in areas with(More)
As part of a complete software stack for autonomous driving, NVIDIA has created a neural-network-based system, known as PilotNet, which outputs steering angles given images of the road ahead. PilotNet is trained using road images paired with the steering angles generated by a human driving a data-collection car. It derives the necessary domain knowledge by(More)
We consider supervised learning with random decision trees, where the tree construction is completely random. The method was used as a heuristic working well in practice despite the simplicity of the setting, but with almost no theoretical guarantees. The goal of this paper is to shed new light on the entire paradigm. We provide strong theoretical(More)
We analyze the performance of the top-down multiclass classification algorithm for decision tree learning called LOMtree, recently proposed in the literature Choromanska and Langford (2014) for solving efficiently classification problems with very large number of classes. The algorithm online optimizes the objective function which simultaneously controls(More)
This paper proposes a new method, that we call VisualBackProp, for visualizing which sets of pixels of the input image contribute most to the predictions made by the convolutional neural network (CNN). The method heavily hinges on exploring the intuition that the feature maps contain less and less irrelevant information to the prediction decision when(More)
We consider an efficient computational framework for speeding up several machine learning algorithms with almost no loss of accuracy. The proposed framework relies on projections via structured matrices that we call Structured Spinners, which are formed as products of three structured matrix-blocks that incorporate rotations. The approach is highly generic,(More)
A new family of Class D resonant inverters is proposed in this paper. Multiple identical series resonant inverters are paralleled using intercell transformers to form phasecontrolled multiphase resonant inverter with a common resonant circuit. Inverters can operate at constant frequency utilizing phase-shift control to regulate output. A frequency-domain(More)
This paper presents a new constant resistance control technique for a cascaded buck and boost converter, which is suitable for wireless energy transfer pickup systems in variable load applications such as battery or ultra-capacitor charging. In order to achieve high efficiency, an impedance matching network is commonly used in the contactless energy(More)
A novel phase control of a semi-bridgeless active rectifier (S-BAR) is investigated in order to utilize the S-BAR in wireless energy transfer applications. The standard receiver side rectifier topology is developed by replacing rectifier lower diodes with synchronous switches controlled by a phase-shifted PWM signal. Theoretical and simulation results show(More)